Replication
All scripts required to reproduce the figures and tables in Population pyramids yield accurate estimates of total fertility rates are contained below.
## Warning: package 'knitr' was built under R version 3.5.3Libraries Required
if (!require("pacman", character.only = TRUE)){
install.packages("pacman", dep = TRUE)
if (!require("pacman", character.only = TRUE))
stop("Package not found")
}
# Libraries
pkgs <- c(
"magick", # magick
"tidyverse", # Tidyverse
"data.table", # Data Management/Manipulation
"readxl", # Microsoft Excel Files
"scales", # Number formatting
"cowplot", # Plot Grids
"tmap", # Cartography
"tmaptools", # Cartographic tools
"tigris", # US shapefiles
"censusapi", # Census Data
"kableExtra", # Pretty Tables
"pdftools", # Load pdfs
"R.utils", # Utilities
"tidycensus", # Census Data
"HMDHFDplus", # Human Mortality Database
"ggrepel", # Formating labels
"ggpubr", # Publication ready plots
"getPass", # Entering Passwords
"raster", # Rasters
"sf", # Shapefiles
"rstan", # STAN
"RColorBrewer", # Colors
"ipumsr", # IPUMS
"openxlsx", # openxlsx
"grid",
"gridExtra",
"numform",
"RJSONIO", # jsonlite
"ggforce"
)
# Install missing packages
# Will only run if at least one package is missing
if(!sum(!p_isinstalled(pkgs))==0){
p_install(
package = pkgs[!p_isinstalled(pkgs)],
character.only = TRUE
)
}
# load the packages
p_load(pkgs, character.only = TRUE)
rm(pkgs)Load the Constants
# s approx 1 - (q5_mult)*q5
qx_const = 0.75
# svd constants for stan model
load('../R/DATA-RAW/svd.constants.RData')Figure 1 and Table 1
Data load and analysis for Figure 1 and Table 1. The script “001-LoadCleanHFDHMDData.R” procues the same file and analysis used in the bTFR calculation below and the production of the iTFR, iTFR\(^+\), xTFR, and xTFR\(^+\) analyses.
Data load
Downloaded HFD and HMD datasets on 6 May 2017:
from HFD - HFD-exposRR.txt (expos by single yr age, country, year)
from HFD - HFD-tfrRR.txt (period TFR by country, year)
from HFD - HFD-totbirthsRR.txt (total births by country, year)
from HMD - HMD_population.zip (zipped file containing a directory called Population5, which in turn contains files called xxxPopulation5.txt that have Jan 1 pop estimates by 5-yr age group for country xxx)
library(HMDHFDplus)
library(tidyverse)
library(ggplot2)
library(grid)
library(gridExtra)
library(openxlsx) # Microsoft Excel Files
# a function to calculate five-year averages of TFR
# given vector X of length L, returns
# NA NA NA NA, mean( X[1:5]), mean(X[2:6]), ..., mean(X[(L-4):L])
mean_lag5 = function(X) {
if (length(X) > 4) {
Z = sapply( 5:length(X), function(i) mean(X[i - 0:4]))
Z = c( rep(NA,4), Z)
} else {
Z = rep(NA, length(X))
}
return(Z)
}
# set up data from Human FERTILITY database files
# remove GBR_NP and DEUTNP observations, because those
# countries are subdivided and we don't want to double count
discard = c('GBR_NP', 'DEUTE', 'DEUTW')
HFD_expos = readHFD('../R/DATA-RAW/HMDHFD/HFD-exposRR.txt') %>%
filter(Age %in% 15:49, !(Code %in% discard)) %>%
mutate(AgeGroup = 5 * floor(Age/5)) %>%
group_by(Code,Year,AgeGroup) %>%
dplyr::summarize(W = sum(Exposure)) %>%
spread(key=AgeGroup, value=W, sep='_') %>%
dplyr::select(Code,Year,W=starts_with('AgeGroup')) %>%
ungroup()
HFD_tfr = readHFD('../R/DATA-RAW/HMDHFD/HFD-tfrRR.txt') %>%
filter(!(Code %in% discard)) %>%
dplyr::select(-TFR40)
HFD_births = readHFD('../R/DATA-RAW/HMDHFD/HFD-totbirthsRR.txt') %>%
filter(!(Code %in% discard)) %>%
dplyr::select(Births=Total, Code=Code, Year=Year)
HMD_population = data.frame()
lt_both = data.frame()
# set up data from Human MORTALITY database files
for (this.country in unique(HFD_expos$Code)) {
filename = paste0(this.country,'.Population5.txt')
unzip(zipfile='../R/DATA-RAW/HMDHFD/HMD_population.zip',
files=paste0('Population5/',filename),
junkpaths=TRUE)
tmp = read.table(filename, skip=2, stringsAsFactors = FALSE,
header=TRUE)
# Some countries have YYYY+ and YYYY- versions of Year, for yrs in
# which territory changed (AK and HI in 1959 US, NF in 1949 Canada, etc)
# In all cases we discard the "-" versions, and remove the "+"
minus_ix = grep('-', tmp$Year)
if (length(minus_ix) > 0) tmp = tmp[-minus_ix, ]
plus_ix = grep('+', tmp$Year)
if (length(plus_ix) > 0) tmp$Year[plus_ix] = substr(tmp$Year,1,4)
tmp = tmp %>%
mutate(Code = this.country,
Year = as.integer(Year))
tmp$Age = c(0,1,seq(5,110,5)) # replace with numeric
tmp = tmp %>%
group_by(Code, Year) %>%
summarize( C = sum(Total[Age %in% 0:1]),
W15 = Female[Age == 15],
W20 = Female[Age == 20],
W25 = Female[Age == 25],
W30 = Female[Age == 30],
W35 = Female[Age == 35],
W40 = Female[Age == 40],
W45 = Female[Age == 45],
W = sum(Female[Age %in% seq(15,45,5)]),
p2534 = (W25+W30)/W,
iTFR = 7*C/W) %>%
ungroup()
HMD_population = rbind(HMD_population, tmp)
file.remove(filename)
} # for this.country
# Merge
for (this.country in unique(HFD_expos$Code)) {
filename = paste0(this.country,'.bltper_1x1.txt')
unzip(zipfile='../R/DATA-RAW/HMDHFD/lt_both.zip',
files=paste0('bltper_1x1/',filename),
junkpaths=TRUE)
tmp = read.table(filename, skip=2, stringsAsFactors = FALSE,
header=TRUE)
# Some countries have YYYY+ and YYYY- versions of Year, for yrs in
# which territory changed (AK and HI in 1959 US, NF in 1949 Canada, etc)
# In all cases we discard the "-" versions, and remove the "+"
minus_ix = grep('-', tmp$Year)
if (length(minus_ix) > 0) tmp = tmp[-minus_ix, ]
plus_ix = grep('+', tmp$Year)
if (length(plus_ix) > 0) tmp$Year[plus_ix] = substr(tmp$Year,1,4)
tmp = tmp %>%
mutate(Code = this.country,
Year = as.integer(Year))
tmp = tmp %>%
filter(Age==0)
lt_both = rbind(lt_both, tmp)
file.remove(filename)
} # for this.country
earliest.year = 1891
tmp1 = left_join(HFD_tfr,
dplyr::select(HMD_population, Code, Year, C, contains('W'), iTFR, p2534),
by=c('Code','Year'))
tmp = left_join(tmp1,
dplyr::select(lt_both, Code, Year, qx, ex),
by=c('Code','Year'))
## calculate the lagged TFR values for each country
tmp$lagTFR = NA
for (this.country in unique(tmp$Code)) {
ix = which(tmp$Code == this.country)
tmp$lagTFR[ix] = mean_lag5( tmp$TFR[ix])
} # for this.country
# write.csv(tmp, file="../R/DATA-PROCESSED/001-LoadCleanHFDHMDData.csv")Bayesian Stan code
WARNING: The bayesian analysis of the entire HFD/HMD database takes approximately 9 hours to run. Here we show a sample of 2 estimates. Changing the variable
nsmallwill change the number of bayesian estimates.
library(dplyr)
library(rstan)
# from program: R/SCRIPTS/load-hmd-hfd-data.R
D = read.csv("../R/DATA-PROCESSED/001-LoadCleanHFDHMDData.csv", as.is=TRUE)
nsmall = 2
D = sample_n(D, nsmall)
load(file='../R/DATA-RAW/svd.constants.RData')
m = svd.constants$m
X = svd.constants$X
# MORTALITY model
# calculate a and b coeffs for each q5 (2 x 159)
ab = sapply(D$qx, function(this.q) {
LearnBayes::beta.select( list(x= this.q/2, p=.05), list(x=this.q*2, p=.95))
})
q5_a = ab[1,]
q5_b = ab[2,]
#--- Wilmoth et al. coefficients from Pop Studies
wilmoth =
read.csv(text = '
age,am,bm,cm,vm,af,bf,cf,vf
0, -0.5101, 0.8164,-0.0245, 0,-0.6619, 0.7684,-0.0277, 0
1, -99, -99, -99, -99, -99, -99, -99, -99
5, -3.0435, 1.5270, 0.0817,0.1720,-2.5608, 1.7937, 0.1082,0.2788
10, -3.9554, 1.2390, 0.0638,0.1683,-3.2435, 1.6653, 0.1088,0.3423
15, -3.9374, 1.0425, 0.0750,0.2161,-3.1099, 1.5797, 0.1147,0.4007
20, -3.4165, 1.1651, 0.0945,0.3022,-2.9789, 1.5053, 0.1011,0.4133
25, -3.4237, 1.1444, 0.0905,0.3624,-3.0185, 1.3729, 0.0815,0.3884
30, -3.4438, 1.0682, 0.0814,0.3848,-3.0201, 1.2879, 0.0778,0.3391
35, -3.4198, 0.9620, 0.0714,0.3779,-3.1487, 1.1071, 0.0637,0.2829
40, -3.3829, 0.8337, 0.0609,0.3530,-3.2690, 0.9339, 0.0533,0.2246
45, -3.4456, 0.6039, 0.0362,0.3060,-3.5202, 0.6642, 0.0289,0.1774
50, -3.4217, 0.4001, 0.0138,0.2564,-3.4076, 0.5556, 0.0208,0.1429
55, -3.4144, 0.1760,-0.0128,0.2017,-3.2587, 0.4461, 0.0101,0.1190
60, -3.1402, 0.0921,-0.0216,0.1616,-2.8907, 0.3988, 0.0042,0.0807
65, -2.8565, 0.0217,-0.0283,0.1216,-2.6608, 0.2591,-0.0135,0.0571
70, -2.4114, 0.0388,-0.0235,0.0864,-2.2949, 0.1759,-0.0229,0.0295
75, -2.0411, 0.0093,-0.0252,0.0537,-2.0414, 0.0481,-0.0354,0.0114
80, -1.6456, 0.0085,-0.0221,0.0316,-1.7308,-0.0064,-0.0347,0.0033
85, -1.3203,-0.0183,-0.0219,0.0061,-1.4473,-0.0531,-0.0327,0.0040
90, -1.0368,-0.0314,-0.0184, 0,-1.1582,-0.0617,-0.0259, 0
95, -0.7310,-0.0170,-0.0133, 0,-0.8655,-0.0598,-0.0198, 0
100,-0.5024,-0.0081,-0.0086, 0,-0.6294,-0.0513,-0.0134, 0
105,-0.3275,-0.0001,-0.0048, 0,-0.4282,-0.0341,-0.0075, 0
110,-0.2212,-0.0028,-0.0027, 0,-0.2966,-0.0229,-0.0041, 0
')
af = wilmoth$af[1:11] # keep age 0,1,...45
bf = wilmoth$bf[1:11] # keep age 0,1,...45
cf = wilmoth$cf[1:11] # keep age 0,1,...45
vf = wilmoth$vf[1:11] # keep age 0,1,...45
########################## INDEP STAN MODEL ##############################################
# STAN MODEL
stanModelText = '
data {
int<lower=0> C; // observed number of children 0-4
vector<lower=0>[7] W; // observed numbef of women 15-19...45-49
real q5_a; // prior will be q(5) ~ beta( q5_a, q5_b)
real q5_b;
real af[11]; // 11 age groups starting at x=0,1,5,10,...,45
real bf[11]; // 11 age groups starting at x=0,1,5,10,...,45
real cf[11]; // 11 age groups starting at x=0,1,5,10,...,45
real vf[11]; // 11 age groups starting at x=0,1,5,10,...,45
vector[7] m; // mean vector for gamma
matrix[7,2] X; // covariance matrix for gamma
}
parameters {
real<lower=0,upper=1> q5; // h = log(q5) in the Wilmoth et al. system
real k; // k = Wilmoth et al. shape parameter
vector[2] beta;
real<lower=0> TFR;
}
transformed parameters {
vector[7] gamma;
real<upper=0> h; // log(q5)
simplex[7] phi; // proportion of total fertility by age group
vector[8] Fx; // age-group fertility rates F10...F45 (F10=0)
real<lower=0> mx[11]; // mortality rates for age groups starting at 0,1,5,10,...45
real<lower=0,upper=1> lx[12]; // life table {lx} values for 0,1,5...,50
real<lower=0,upper=5> Lx[10]; // life table {5Lx} values for 0,5...,45
vector[7] Kx; // expected surviving children 0-4 per woman
// in age group x to x+4
real Kstar; // expected surviving total number of children
//--- child mortality index for Wilmoth model
h = log(q5);
//--- fertility rates
gamma = m + X * beta;
for (i in 1:7) phi[i] = exp(gamma[i]) / sum( exp(gamma));
Fx[1] = 0; // F10
for (i in 2:8) Fx[i] = TFR * phi[i-1] / 5; // F15...F45
//--- mortality rates, life table survival probs, and big L values
for (i in 1:11) { mx[i] = exp( af[i] + bf[i]*h + cf[i]*square(h) + vf[i]*k ); }
mx[2] = -0.25 * (mx[1] + log(1-q5) ); // recalculate 1_mu_4 = -1/4 log(l[5]/l[1])
lx[1] = 1; // x=0
lx[2] = lx[1] * exp(-mx[1]); // x=1
lx[3] = lx[2] * exp(-4*mx[2]); // x=5
for (i in 3:12) lx[i] = lx[i-1] * exp(-5*mx[i-1]); // x=5,10,...50
Lx[1] = 1* (lx[1]+lx[2])/2 + 4*(lx[2]+lx[3])/2 ; // 5L0
for (i in 2:10) Lx[i] = 5* (lx[i+1]+lx[1+2])/2 ; // 5Lx
//--- main result: expected surviving 0-4 yr olds per woman in each age group
// indexing is a bit complicated:
// Lx[1:10] is for age groups 0,5,...,45
// Fx[1:8] is for age groups 10,15,...,45
// Kx[1:7] is for age groups 15,...,45
for (i in 1:7) Kx[i] = (Lx[i+2]/Lx[i+3] * Fx[i] + Fx[i+1]) * Lx[1]/2 ;
Kstar = dot_product(W, Kx);
}
model {
// LIKELIHOOD
C ~ poisson(Kstar);
// PRIORS
beta ~ normal(0,1);
q5 ~ beta(q5_a, q5_b); // 90% prior prob. that q5 is between 1/2 and 2x estimated q5
k ~ normal(0,1);
}'
MODEL = stan_model(model_code=stanModelText, model_name='single schedule TFR')
# construct the matrix of constants for cumulative hazard calculations
n = c(1,5, rep(5,9)) # widths of life table age intervals for x=0,1,5,10...45
cs_constants = matrix(0, 11, 12)
for (j in 1:11) cs_constants[1:j,j+1] = head(n,j)
# construct the constants for the trapezoidal approx of L0...L45 from a row of l0,l1,l5,l10,...,l50
trapez_constants = matrix(0, 12, 10,
dimnames=list(paste0('l', c(0,1,seq(5,50,5))), paste0('L', seq(0,45,5))))
trapez_constants[c('l0','l1','l5'), 'L0'] = c( 1/2, 5/2, 4/2)
for (j in 2:10) trapez_constants[j+1:2, j] = 5/2
stanInits = function(nchains=1) {
L = vector('list',nchains)
for (i in seq(L)) {
L[[i]] = list(
q5 = rbeta(1, shape1=q5_a, shape2=q5_b),
k = rnorm(1, mean=0,sd=1),
beta = runif(2, min=-.10, max=.10),
TFR = pmax( .10, rnorm(1, 2, sd=.50))
)
}
return(L)
} # stanInits
# LOOP OVER SCHEDULES
results = data.frame()
for (k in 1:nrow(D)) {
print(paste('...starting', k, 'of', nrow(D) ))
stanDataList = list(
C = round(D$C[k]),
W = as.numeric( D[k, paste0('W',seq(15,45,5))]),
q5_a = q5_a[k],
q5_b = q5_b[k],
af = af,
bf = bf,
cf = cf,
vf = vf,
cs_constants = cs_constants,
trapez_constants = trapez_constants,
m = m,
X = t(X) # 7x2 in this version
)
# MCMC
nchains = 4
fit = sampling(MODEL,
data = stanDataList,
pars = c('TFR','beta','q5'),
init = stanInits(nchains),
seed = 6447100,
iter = 900,
warmup = 300,
thin = 4,
chains = nchains,
control = list(max_treedepth = 12))
tmp = as.data.frame( summary(fit, 'TFR', probs=c(.10,.25,.50,.75,.90))$summary )
names(tmp) = c('post_mean','se_mean','sd',paste0('Q',c(10,25,50,75,90)),'n_eff','Rhat')
tmp$Code = D$Code[k]
tmp$Year = D$Year[k]
tmp$iTFR = D$iTFR[k]
tmp$lagTFR = D$lagTFR[k]
tmp = dplyr::select(tmp, Code: lagTFR, post_mean, contains('Q'),n_eff,Rhat) %>%
mutate_at(vars(iTFR:Rhat), round, digits=3)
results = rbind( results, tmp)
} # for k## [1] "...starting 1 of 2"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 3.144 seconds (Warm-up)
## Chain 1: 1.02 seconds (Sampling)
## Chain 1: 4.164 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 3.235 seconds (Warm-up)
## Chain 2: 0.885 seconds (Sampling)
## Chain 2: 4.12 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 3.371 seconds (Warm-up)
## Chain 3: 1.025 seconds (Sampling)
## Chain 3: 4.396 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 3.81 seconds (Warm-up)
## Chain 4: 1.199 seconds (Sampling)
## Chain 4: 5.009 seconds (Total)
## Chain 4:
## [1] "...starting 2 of 2"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 2.616 seconds (Warm-up)
## Chain 1: 0.437 seconds (Sampling)
## Chain 1: 3.053 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 2.633 seconds (Warm-up)
## Chain 2: 0.429 seconds (Sampling)
## Chain 2: 3.062 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 2.201 seconds (Warm-up)
## Chain 3: 0.342 seconds (Sampling)
## Chain 3: 2.543 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 2.066 seconds (Warm-up)
## Chain 4: 0.398 seconds (Sampling)
## Chain 4: 2.464 seconds (Total)
## Chain 4:rownames(results) = NULL
results## Code Year iTFR lagTFR post_mean Q10 Q25 Q50 Q75 Q90
## 1 BLR 1985 2.252 2.061 2.194 2.119 2.152 2.189 2.232 2.272
## 2 GBR_SCO 1996 1.723 1.599 1.645 1.620 1.629 1.642 1.657 1.675
## n_eff Rhat
## 1 562.045 1.003
## 2 208.320 1.007# write.csv(results, "../R/DATA-PROCESSED/HFD-bayesitfr.csv")Data Analysis
This code will merge the HMD/HFD with the DHS data and calculate the xTFR coeffficients.
Note: This code chunk with pull in Bayesian TFR estimates of the DHS data. Those estimates are produced in the code chunk immediately following this one.
# Load the bTFR results.
bayesTFR <- read_csv("../R/DATA-PROCESSED/HFD-bayesitfr.csv") %>%
dplyr::select(Code, Year, iTFR, lagTFR, bayesTFR=post_mean)
bayesTFR_dhs <- read_csv("../R/DATA-PROCESSED/IPUMS-bayesitfr.csv") %>%
mutate(Year = as.character(Year)) %>%
dplyr::select(Code, Year, bTFR=post_mean)
earliest.year = 1891
tmp = read.csv("../R/DATA-PROCESSED/001-LoadCleanHFDHMDData.csv", as.is=TRUE) %>%
filter(Year >= earliest.year, !is.na(iTFR)) %>%
mutate( CWR = C/W,
mult = lagTFR/CWR,
p15 = W15/W,
p20 = W20/W,
p25 = W25/W,
p30 = W30/W,
p35 = W35/W,
p40 = W40/W,
p45 = W45/W,
decade = as.factor( 10 * floor(Year/10)) ) %>%
filter(!is.na(mult))
within10percent <- mean( abs((tmp$mult-7)/7) < .10)
reg = lm( mult ~ p2534, data=tmp)
reg2 = lm( mult ~ -1+p15+p20+p25+p30+p35+p40+p45, data=tmp)
# Coefficients from Rele 1974. We did not use this analysis in the final paper.
relecoefficients <- tribble(
~"e0", ~"alpha", ~"deltaa", ~"beta", ~"deltab",
20L, 0.0547, -0.00263, 4.768, -0.04387,
30L, 0.0284, -0.00155, 4.3293, -0.02676,
40L, 0.0129, -0.00188, 4.0617, -0.02028,
50L, -0.0059, -0.00123, 3.8589, -0.01961,
60L, -0.0182, -0.00127, 3.6628, -0.01799,
70L, -0.0309, 0, 3.4829, 0,
80L, -0.0309, 0, 3.4829, 0,
90L,-0.0309, 0, 3.4829, 0
)
# Calculating the xTFR based on the regression components
xitfr <- tmp %>%
mutate( "xTFR+" = (coef(reg)[1] + coef(reg)[2] * p2534) * ((C/(1-qx_const*qx))/W),
"iTFR+" = 7 * ((C/(1-qx_const*qx))/W),
iTFR = 7* C/W,
xTFR = (coef(reg)[1] + coef(reg)[2] * p2534) * (C/W),
e0 = plyr::round_any(ex, 10, floor)) %>%
left_join(., relecoefficients) %>%
mutate(eadj = ex-e0,
eadja = alpha + eadj*deltaa,
eadjb = beta + eadj*deltab,
rele = (1+1.05)*(eadja+(eadjb*(C/W)))) %>%
na.omit
xtfr_alpha = round(coef(reg)[1],2)
xtfr_beta = round(coef(reg)[2],2)
beta = coef(reg2)
## Getting the DHS data.
# require(RJSONIO)
# # Import DHS Indicator data for TFR for each survey
# tfr <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/FE_FRTR_W_TFR?perpage=1000")
# under5mort <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/CM_ECMR_C_U5M?perpage=1000")
# f1549 <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/FE_FRTY_W_NPG?perpage=1000")
# c00045 <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/ML_FEVR_C_NUM?perpage=1000")
#
# # Unlist the JSON file entries
# under5mort <- lapply(under5mort$Data, function(x) { unlist(x) })
# tfr <- lapply(tfr$Data, function(x) { unlist(x) })
# f1549 <- lapply(f1549$Data, function(x) { unlist(x) })
# c00045 <- lapply(c00045$Data, function(x) { unlist(x) })
#
# # Convert JSON input to a data frame
# under5mort <- as.data.frame(do.call("rbind", under5mort),stringsAsFactors=FALSE)
# under5mort <- under5mort %>%
# filter(IsPreferred == 1) %>%# This gets just the 5-years preceding the survey.
# dplyr::select(SurveyId, u5mort = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
#
# tfr <- as.data.frame(do.call("rbind", tfr),stringsAsFactors=FALSE)%>%
# dplyr::select(SurveyId, TFR = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
#
# f1549 <- as.data.frame(do.call("rbind", f1549),stringsAsFactors=FALSE) %>%
# dplyr::select(SurveyId, W = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
#
# c00045 <- as.data.frame(do.call("rbind", c00045),stringsAsFactors=FALSE) %>%
# dplyr::select(SurveyId, C = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
#
# write_csv(tfr, "../R/DATA-PROCESSED/DHS_TFR.csv")
# write_csv(f1549, "../R/DATA-PROCESSED/DHS_f1549.csv")
# write_csv(c00045, "../R/DATA-PROCESSED/DHS_c00045.csv")
# write_csv(under5mort, "../R/DATA-PROCESSED/DHS_under5mort.csv")
# DHS Data reimport
tfr <- read_csv("../R/DATA-PROCESSED/DHS_TFR.csv")
f1549 <- read_csv("../R/DATA-PROCESSED/DHS_f1549.csv")
c00045 <- read_csv("../R/DATA-PROCESSED/DHS_c00045.csv")
under5mort <- read_csv("../R/DATA-PROCESSED/DHS_under5mort.csv")
# Unzip the # of women from
gunzip("../R/DATA-RAW/DHS/idhs_00020.dat.gz", overwrite = TRUE, remove = FALSE)
ddi <- ipumsr::read_ipums_ddi("../R/DATA-RAW/DHS/idhs_00020.xml")
women <- ipumsr::read_ipums_micro(ddi) %>%
group_by(COUNTRY, YEAR, AGE5YEAR) %>%
dplyr::summarise(women = sum(PERWEIGHT)) %>%
spread(AGE5YEAR, women) %>%
dplyr::select(COUNTRY, Year = YEAR, W15 = `20`, W20 = `30`, W25 = `40`, W30 = `50`, W35 = `60`, W40 = `70`, W45 = `80`) %>%
ungroup() %>%
mutate(W2 = W15 + W20 + W25 + W30 + W35 + W40 + W45,
Year = as.character(Year),
Name = case_when(
COUNTRY == '004' ~ 'Afghanistan',
COUNTRY == '050' ~ 'Bangladesh',
COUNTRY == '104' ~ 'Myanmar',
COUNTRY == '108' ~ 'Burundi',
COUNTRY == '116' ~ 'Cambodia',
COUNTRY == '120' ~ 'Cameroon',
COUNTRY == '148' ~ 'Chad',
COUNTRY == '180' ~ 'Congo Democratic Republic',
COUNTRY == '204' ~ 'Benin',
COUNTRY == '231' ~ 'Ethiopia',
COUNTRY == '288' ~ 'Ghana',
COUNTRY == '320' ~ 'Guatemala',
COUNTRY == '324' ~ 'Guinea',
COUNTRY == '356' ~ 'India',
COUNTRY == '384' ~ 'Cote dIvoire',
COUNTRY == '404' ~ 'Kenya',
COUNTRY == '426' ~ 'Lesotho',
COUNTRY == '450' ~ 'Madagascar',
COUNTRY == '454' ~ 'Malawi',
COUNTRY == '466' ~ 'Mali',
COUNTRY == '504' ~ 'Morocco',
COUNTRY == '508' ~ 'Mozambique',
COUNTRY == '516' ~ 'Namibia',
COUNTRY == '524' ~ 'Nepal',
COUNTRY == '562' ~ 'Niger',
COUNTRY == '586' ~ 'Pakistan',
COUNTRY == '566' ~ 'Nigeria',
COUNTRY == '604' ~ 'Peru',
COUNTRY == '646' ~ 'Rwanda',
COUNTRY == '686' ~ 'Senegal',
COUNTRY == '710' ~ 'South Africa',
COUNTRY == '716' ~ 'Zimbabwe',
COUNTRY == '729' ~ 'Sudan',
COUNTRY == '788' ~ 'Tunisia',
COUNTRY == '792' ~ 'Turkey',
COUNTRY == '800' ~ 'Uganda',
COUNTRY == '818' ~ 'Egypt',
COUNTRY == '834' ~ 'Tanzania',
COUNTRY == '854' ~ 'Burkina Faso',
COUNTRY == '887' ~ 'Yemen',
COUNTRY == '894' ~ 'Zambia',
COUNTRY == '1' ~ 'Model'
),
Code = case_when(
COUNTRY == '004' ~ 'AF',
COUNTRY == '050' ~ 'BD',
COUNTRY == '104' ~ 'MM',
COUNTRY == '108' ~ 'BU',
COUNTRY == '116' ~ 'KH',
COUNTRY == '120' ~ 'CM',
COUNTRY == '148' ~ 'TD',
COUNTRY == '180' ~ 'CD',
COUNTRY == '204' ~ 'BJ',
COUNTRY == '231' ~ 'ET',
COUNTRY == '288' ~ 'GH',
COUNTRY == '320' ~ 'GU',
COUNTRY == '324' ~ 'GN',
COUNTRY == '356' ~ 'IA',
COUNTRY == '384' ~ 'CI',
COUNTRY == '404' ~ 'KE',
COUNTRY == '426' ~ 'LS',
COUNTRY == '450' ~ 'MD',
COUNTRY == '454' ~ 'MW',
COUNTRY == '466' ~ 'ML',
COUNTRY == '504' ~ 'MA',
COUNTRY == '508' ~ 'MZ',
COUNTRY == '516' ~ 'NM',
COUNTRY == '524' ~ 'NP',
COUNTRY == '562' ~ 'NI',
COUNTRY == '586' ~ 'PK',
COUNTRY == '566' ~ 'NG',
COUNTRY == '604' ~ 'PE',
COUNTRY == '646' ~ 'RW',
COUNTRY == '686' ~ 'SN',
COUNTRY == '710' ~ 'ZA',
COUNTRY == '716' ~ 'ZW',
COUNTRY == '729' ~ 'SD',
COUNTRY == '788' ~ 'TN',
COUNTRY == '792' ~ 'TR',
COUNTRY == '800' ~ 'UG',
COUNTRY == '818' ~ 'EG',
COUNTRY == '834' ~ 'TZ',
COUNTRY == '854' ~ 'BF',
COUNTRY == '887' ~ 'YE',
COUNTRY == '894' ~ 'ZM'
))## Use of data from IPUMS-DHS is subject to conditions including that users should
## cite the data appropriately. Use command `ipums_conditions()` for more details.dat <- left_join(c00045, under5mort) %>%
left_join(., tfr) %>%
left_join(., f1549) %>%
mutate(iTFR = as.numeric(C) / as.numeric(W) * 7,
TFR = as.numeric(TFR),
source = "DHS",
xTFR = 0,
W = as.numeric(W),
C = as.numeric(C),
q5 = as.numeric(u5mort)/1000,
`iTFR+` = 7 * ((C/(1-qx_const*q5))/W),
`xTFR+` = NA,
rele = NA,
SurveyYear = as.character(SurveyYear)) %>%
dplyr::select(Code = DHS_CountryCode, Year = SurveyYear, iTFR, xTFR, C, lagTFR=TFR, q5, 'iTFR+', 'xTFR+', rele, source,W) %>%
left_join(., women) %>%
mutate(p2534 = (W25 + W30)/ W,
xTFR = (coef(reg)[1] + coef(reg)[2] * p2534) * (C/W),
`xTFR+` = (coef(reg)[1] + coef(reg)[2] * p2534) * ((C/(1-qx_const*q5))/W)) %>%
dplyr::select(Code, Year, iTFR, xTFR, C, W, lagTFR, q5, 'iTFR+', 'xTFR+', rele, source)
dat <- left_join(dat, bayesTFR_dhs)
# Joining the iTFR, xTFR, and BayesTFR together
big = inner_join(xitfr, bayesTFR, c("Code", "Year")) %>%
dplyr::select(Code, Year, iTFR=iTFR.x, xTFR, C, W, lagTFR=lagTFR.x, q5=qx, bTFR=bayesTFR, 'iTFR+', 'xTFR+', rele) %>%
mutate(source = "HMD/HFD")
big <- rbind(big, dat) %>%
mutate(Year = as.numeric(Year))
# Summary Statistics for each method
itfrape50 <- quantile(abs((big$iTFR-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
itfrape90 <- quantile(abs((big$iTFR-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
xtfrape50 <- quantile(abs((big$xTFR-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
xtfrape90 <- quantile(abs((big$xTFR-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
releape50 <- quantile(abs((big$rele-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
releape90 <- quantile(abs((big$rele-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
itfr_hatape50 <- quantile(abs((big$"iTFR+"-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
itfr_hatape90 <- quantile(abs((big$"iTFR+"-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
xtfr_hatape50 <- quantile(abs((big$"xTFR+"-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
xtfr_hatape90 <- quantile(abs((big$"xTFR+"-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
bayestfrape50 <- quantile(abs((big$bTFR-big$lagTFR)/big$lagTFR)*100, 0.5, na.rm=T)
bayestfrape90 <- quantile(abs((big$bTFR-big$lagTFR)/big$lagTFR)*100, 0.9, na.rm=T)
itfrabs50 <- quantile(abs((big$iTFR-big$lagTFR)), 0.5, na.rm=T)
itfrabs90 <- quantile(abs((big$iTFR-big$lagTFR)), 0.9, na.rm=T)
xtfrabs50 <- quantile(abs((big$xTFR-big$lagTFR)), 0.5, na.rm=T)
xtfrabs90 <- quantile(abs((big$xTFR-big$lagTFR)), 0.9, na.rm=T)
itfr_hatabs50 <- quantile(abs((big$"iTFR+"-big$lagTFR)), 0.5, na.rm=T)
itfr_hatabs90 <- quantile(abs((big$"iTFR+"-big$lagTFR)), 0.9, na.rm=T)
xtfr_hatabs50 <- quantile(abs((big$"xTFR+"-big$lagTFR)), 0.5, na.rm=T)
xtfr_hatabs90 <- quantile(abs((big$"xTFR+"-big$lagTFR)), 0.9, na.rm=T)
bayestfrabs50 <- quantile(abs((big$bTFR-big$lagTFR)), 0.5, na.rm=T)
bayestfrabs90 <- quantile(abs((big$bTFR-big$lagTFR)), 0.9, na.rm=T)DHS bTFR estimates
library(dplyr)
library(rstan)
## Getting the DHS data.
require(RJSONIO)
# Import DHS Indicator data for TFR for each survey
tfr <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/FE_FRTR_W_TFR?perpage=1000")
under5mort <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/CM_ECMR_C_U5M?perpage=1000")
f1549 <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/FE_FRTY_W_NPG?perpage=1000")
c00045 <- fromJSON("http://api.dhsprogram.com/rest/dhs/data/ML_FEVR_C_NUM?perpage=1000")
# Unlist the JSON file entries
under5mort <- lapply(under5mort$Data, function(x) { unlist(x) })
tfr <- lapply(tfr$Data, function(x) { unlist(x) })
f1549 <- lapply(f1549$Data, function(x) { unlist(x) })
c00045 <- lapply(c00045$Data, function(x) { unlist(x) })
# Convert JSON input to a data frame
under5mort <- as.data.frame(do.call("rbind", under5mort),stringsAsFactors=FALSE)
under5mort <- under5mort %>%
filter(IsPreferred == 1) %>%# This gets just the 5-years preceding the survey.
dplyr::select(SurveyId, u5mort = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
tfr <- as.data.frame(do.call("rbind", tfr),stringsAsFactors=FALSE)%>%
dplyr::select(SurveyId, TFR = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
f1549 <- as.data.frame(do.call("rbind", f1549),stringsAsFactors=FALSE) %>%
dplyr::select(SurveyId, W = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
c00045 <- as.data.frame(do.call("rbind", c00045),stringsAsFactors=FALSE) %>%
dplyr::select(SurveyId, C = Value, SurveyYearLabel, SurveyYear, DHS_CountryCode, CountryName)
gunzip("../R/DATA-RAW/DHS/idhs_00020.dat.gz", overwrite = TRUE, remove = FALSE)
ddi <- ipumsr::read_ipums_ddi("../R/DATA-RAW/DHS/idhs_00020.xml")
women <- ipumsr::read_ipums_micro(ddi) %>%
group_by(COUNTRY, YEAR, AGE5YEAR) %>%
dplyr::summarise(women = sum(PERWEIGHT)) %>%
spread(AGE5YEAR, women) %>%
dplyr::select(COUNTRY, Year = YEAR, W15 = `20`, W20 = `30`, W25 = `40`, W30 = `50`, W35 = `60`, W40 = `70`, W45 = `80`) %>%
ungroup() %>%
mutate(W2 = W15 + W20 + W25 + W30 + W35 + W40 + W45,
Year = as.character(Year),
Name = case_when(
COUNTRY == '004' ~ 'Afghanistan',
COUNTRY == '050' ~ 'Bangladesh',
COUNTRY == '104' ~ 'Myanmar',
COUNTRY == '108' ~ 'Burundi',
COUNTRY == '116' ~ 'Cambodia',
COUNTRY == '120' ~ 'Cameroon',
COUNTRY == '148' ~ 'Chad',
COUNTRY == '180' ~ 'Congo Democratic Republic',
COUNTRY == '204' ~ 'Benin',
COUNTRY == '231' ~ 'Ethiopia',
COUNTRY == '288' ~ 'Ghana',
COUNTRY == '320' ~ 'Guatemala',
COUNTRY == '324' ~ 'Guinea',
COUNTRY == '356' ~ 'India',
COUNTRY == '384' ~ 'Cote dIvoire',
COUNTRY == '404' ~ 'Kenya',
COUNTRY == '426' ~ 'Lesotho',
COUNTRY == '450' ~ 'Madagascar',
COUNTRY == '454' ~ 'Malawi',
COUNTRY == '466' ~ 'Mali',
COUNTRY == '504' ~ 'Morocco',
COUNTRY == '508' ~ 'Mozambique',
COUNTRY == '516' ~ 'Namibia',
COUNTRY == '524' ~ 'Nepal',
COUNTRY == '562' ~ 'Niger',
COUNTRY == '586' ~ 'Pakistan',
COUNTRY == '566' ~ 'Nigeria',
COUNTRY == '604' ~ 'Peru',
COUNTRY == '646' ~ 'Rwanda',
COUNTRY == '686' ~ 'Senegal',
COUNTRY == '710' ~ 'South Africa',
COUNTRY == '716' ~ 'Zimbabwe',
COUNTRY == '729' ~ 'Sudan',
COUNTRY == '788' ~ 'Tunisia',
COUNTRY == '792' ~ 'Turkey',
COUNTRY == '800' ~ 'Uganda',
COUNTRY == '818' ~ 'Egypt',
COUNTRY == '834' ~ 'Tanzania',
COUNTRY == '854' ~ 'Burkina Faso',
COUNTRY == '887' ~ 'Yemen',
COUNTRY == '894' ~ 'Zambia',
COUNTRY == '1' ~ 'Model'
),
Code = case_when(
COUNTRY == '004' ~ 'AF',
COUNTRY == '050' ~ 'BD',
COUNTRY == '104' ~ 'MM',
COUNTRY == '108' ~ 'BU',
COUNTRY == '116' ~ 'KH',
COUNTRY == '120' ~ 'CM',
COUNTRY == '148' ~ 'TD',
COUNTRY == '180' ~ 'CD',
COUNTRY == '204' ~ 'BJ',
COUNTRY == '231' ~ 'ET',
COUNTRY == '288' ~ 'GH',
COUNTRY == '320' ~ 'GU',
COUNTRY == '324' ~ 'GN',
COUNTRY == '356' ~ 'IA',
COUNTRY == '384' ~ 'CI',
COUNTRY == '404' ~ 'KE',
COUNTRY == '426' ~ 'LS',
COUNTRY == '450' ~ 'MD',
COUNTRY == '454' ~ 'MW',
COUNTRY == '466' ~ 'ML',
COUNTRY == '504' ~ 'MA',
COUNTRY == '508' ~ 'MZ',
COUNTRY == '516' ~ 'NM',
COUNTRY == '524' ~ 'NP',
COUNTRY == '562' ~ 'NI',
COUNTRY == '586' ~ 'PK',
COUNTRY == '566' ~ 'NG',
COUNTRY == '604' ~ 'PE',
COUNTRY == '646' ~ 'RW',
COUNTRY == '686' ~ 'SN',
COUNTRY == '710' ~ 'ZA',
COUNTRY == '716' ~ 'ZW',
COUNTRY == '729' ~ 'SD',
COUNTRY == '788' ~ 'TN',
COUNTRY == '792' ~ 'TR',
COUNTRY == '800' ~ 'UG',
COUNTRY == '818' ~ 'EG',
COUNTRY == '834' ~ 'TZ',
COUNTRY == '854' ~ 'BF',
COUNTRY == '887' ~ 'YE',
COUNTRY == '894' ~ 'ZM'
))## Use of data from IPUMS-DHS is subject to conditions including that users should
## cite the data appropriately. Use command `ipums_conditions()` for more details.qx_const = 0.75
dat <- left_join(c00045, under5mort) %>%
left_join(., tfr) %>%
left_join(., f1549) %>%
mutate(iTFR = as.numeric(C) / as.numeric(W) * 7,
TFR = as.numeric(TFR),
source = "DHS",
xTFR = 0,
W = as.numeric(W),
C = as.numeric(C),
qx = as.numeric(u5mort)/1000,
`iTFR+` = 7 * ((C/(1-qx_const*qx))/W),
`xTFR+` = NA) %>%
dplyr::select(Code = DHS_CountryCode, Year = SurveyYear, iTFR, xTFR, C, lagTFR=TFR, qx, 'iTFR+', 'xTFR+', source,W) %>%
left_join(., women) %>%
mutate(p2534 = (W25 + W30)/ W,
xTFR = (coef(reg)[1] + coef(reg)[2] * p2534) * (C/W),
`xTFR+` = (coef(reg)[1] + coef(reg)[2] * p2534) * ((C/(1-qx_const*qx))/W)) %>%
na.omit
D <- dat
load(file='../R/DATA-RAW/svd.constants.RData')
m = svd.constants$m
X = svd.constants$X
ab = sapply(D$qx, function(this.q) {
LearnBayes::beta.select( list(x= this.q/2, p=.05), list(x=this.q*2, p=.95))
})
q5_a = ab[1,]
q5_b = ab[2,]
#--- Wilmoth et al. coefficients from Pop Studies
wilmoth =
read.csv(text = '
age,am,bm,cm,vm,af,bf,cf,vf
0, -0.5101, 0.8164,-0.0245, 0,-0.6619, 0.7684,-0.0277, 0
1, -99, -99, -99, -99, -99, -99, -99, -99
5, -3.0435, 1.5270, 0.0817,0.1720,-2.5608, 1.7937, 0.1082,0.2788
10, -3.9554, 1.2390, 0.0638,0.1683,-3.2435, 1.6653, 0.1088,0.3423
15, -3.9374, 1.0425, 0.0750,0.2161,-3.1099, 1.5797, 0.1147,0.4007
20, -3.4165, 1.1651, 0.0945,0.3022,-2.9789, 1.5053, 0.1011,0.4133
25, -3.4237, 1.1444, 0.0905,0.3624,-3.0185, 1.3729, 0.0815,0.3884
30, -3.4438, 1.0682, 0.0814,0.3848,-3.0201, 1.2879, 0.0778,0.3391
35, -3.4198, 0.9620, 0.0714,0.3779,-3.1487, 1.1071, 0.0637,0.2829
40, -3.3829, 0.8337, 0.0609,0.3530,-3.2690, 0.9339, 0.0533,0.2246
45, -3.4456, 0.6039, 0.0362,0.3060,-3.5202, 0.6642, 0.0289,0.1774
50, -3.4217, 0.4001, 0.0138,0.2564,-3.4076, 0.5556, 0.0208,0.1429
55, -3.4144, 0.1760,-0.0128,0.2017,-3.2587, 0.4461, 0.0101,0.1190
60, -3.1402, 0.0921,-0.0216,0.1616,-2.8907, 0.3988, 0.0042,0.0807
65, -2.8565, 0.0217,-0.0283,0.1216,-2.6608, 0.2591,-0.0135,0.0571
70, -2.4114, 0.0388,-0.0235,0.0864,-2.2949, 0.1759,-0.0229,0.0295
75, -2.0411, 0.0093,-0.0252,0.0537,-2.0414, 0.0481,-0.0354,0.0114
80, -1.6456, 0.0085,-0.0221,0.0316,-1.7308,-0.0064,-0.0347,0.0033
85, -1.3203,-0.0183,-0.0219,0.0061,-1.4473,-0.0531,-0.0327,0.0040
90, -1.0368,-0.0314,-0.0184, 0,-1.1582,-0.0617,-0.0259, 0
95, -0.7310,-0.0170,-0.0133, 0,-0.8655,-0.0598,-0.0198, 0
100,-0.5024,-0.0081,-0.0086, 0,-0.6294,-0.0513,-0.0134, 0
105,-0.3275,-0.0001,-0.0048, 0,-0.4282,-0.0341,-0.0075, 0
110,-0.2212,-0.0028,-0.0027, 0,-0.2966,-0.0229,-0.0041, 0
')
af = wilmoth$af[1:11] # keep age 0,1,...45
bf = wilmoth$bf[1:11] # keep age 0,1,...45
cf = wilmoth$cf[1:11] # keep age 0,1,...45
vf = wilmoth$vf[1:11] # keep age 0,1,...45
########################## INDEP STAN MODEL ##############################################
# STAN MODEL
stanModelText = '
data {
int<lower=0> C; // observed number of children 0-4
vector<lower=0>[7] W; // observed numbef of women 15-19...45-49
real q5_a; // prior will be q(5) ~ beta( q5_a, q5_b)
real q5_b;
real af[11]; // 11 age groups starting at x=0,1,5,10,...,45
real bf[11]; // 11 age groups starting at x=0,1,5,10,...,45
real cf[11]; // 11 age groups starting at x=0,1,5,10,...,45
real vf[11]; // 11 age groups starting at x=0,1,5,10,...,45
vector[7] m; // mean vector for gamma
matrix[7,2] X; // covariance matrix for gamma
}
parameters {
real<lower=0,upper=1> q5; // h = log(q5) in the Wilmoth et al. system
real k; // k = Wilmoth et al. shape parameter
vector[2] beta;
real<lower=0> TFR;
}
transformed parameters {
vector[7] gamma;
real<upper=0> h; // log(q5)
simplex[7] phi; // proportion of total fertility by age group
vector[8] Fx; // age-group fertility rates F10...F45 (F10=0)
real<lower=0> mx[11]; // mortality rates for age groups starting at 0,1,5,10,...45
real<lower=0,upper=1> lx[12]; // life table {lx} values for 0,1,5...,50
real<lower=0,upper=5> Lx[10]; // life table {5Lx} values for 0,5...,45
vector[7] Kx; // expected surviving children 0-4 per woman
// in age group x to x+4
real Kstar; // expected surviving total number of children
//--- child mortality index for Wilmoth model
h = log(q5);
//--- fertility rates
gamma = m + X * beta;
for (i in 1:7) phi[i] = exp(gamma[i]) / sum( exp(gamma));
Fx[1] = 0; // F10
for (i in 2:8) Fx[i] = TFR * phi[i-1] / 5; // F15...F45
//--- mortality rates, life table survival probs, and big L values
for (i in 1:11) { mx[i] = exp( af[i] + bf[i]*h + cf[i]*square(h) + vf[i]*k ); }
mx[2] = -0.25 * (mx[1] + log(1-q5) ); // recalculate 1_mu_4 = -1/4 log(l[5]/l[1])
lx[1] = 1; // x=0
lx[2] = lx[1] * exp(-mx[1]); // x=1
lx[3] = lx[2] * exp(-4*mx[2]); // x=5
for (i in 3:12) lx[i] = lx[i-1] * exp(-5*mx[i-1]); // x=5,10,...50
Lx[1] = 1* (lx[1]+lx[2])/2 + 4*(lx[2]+lx[3])/2 ; // 5L0
for (i in 2:10) Lx[i] = 5* (lx[i+1]+lx[1+2])/2 ; // 5Lx
//--- main result: expected surviving 0-4 yr olds per woman in each age group
// indexing is a bit complicated:
// Lx[1:10] is for age groups 0,5,...,45
// Fx[1:8] is for age groups 10,15,...,45
// Kx[1:7] is for age groups 15,...,45
for (i in 1:7) Kx[i] = (Lx[i+2]/Lx[i+3] * Fx[i] + Fx[i+1]) * Lx[1]/2 ;
Kstar = dot_product(W, Kx);
}
model {
// LIKELIHOOD
C ~ poisson(Kstar);
// PRIORS
beta ~ normal(0,1);
q5 ~ beta(q5_a, q5_b); // 90% prior prob. that q5 is between 1/2 and 2x estimated q5
k ~ normal(0,1);
}'
MODEL = stan_model(model_code=stanModelText, model_name='single schedule TFR')
# construct the matrix of constants for cumulative hazard calculations
n = c(1,5, rep(5,9)) # widths of life table age intervals for x=0,1,5,10...45
cs_constants = matrix(0, 11, 12)
for (j in 1:11) cs_constants[1:j,j+1] = head(n,j)
# construct the constants for the trapezoidal approx of L0...L45 from a row of l0,l1,l5,l10,...,l50
trapez_constants = matrix(0, 12, 10,
dimnames=list(paste0('l', c(0,1,seq(5,50,5))), paste0('L', seq(0,45,5))))
trapez_constants[c('l0','l1','l5'), 'L0'] = c( 1/2, 5/2, 4/2)
for (j in 2:10) trapez_constants[j+1:2, j] = 5/2
stanInits = function(nchains=1) {
L = vector('list',nchains)
for (i in seq(L)) {
L[[i]] = list(
q5 = rbeta(1, shape1=q5_a, shape2=q5_b),
k = rnorm(1, mean=0,sd=1),
beta = runif(2, min=-.10, max=.10),
TFR = pmax( .10, rnorm(1, 2, sd=.50))
)
}
return(L)
} # stanInits
# LOOP OVER SCHEDULES
results = data.frame()
for (k in 1:nrow(D)) {
print(paste('...starting', k, 'of', nrow(D) ))
stanDataList = list(
C = round(D$C[k]),
W = as.numeric( D[k, paste0('W',seq(15,45,5))]),
q5_a = q5_a[k],
q5_b = q5_b[k],
af = af,
bf = bf,
cf = cf,
vf = vf,
cs_constants = cs_constants,
trapez_constants = trapez_constants,
m = m,
X = t(X) # 7x2 in this version
)
# MCMC
nchains = 4
fit = sampling(MODEL,
data = stanDataList,
pars = c('TFR','beta','q5'),
init = stanInits(nchains),
seed = 6447100,
iter = 900,
warmup = 300,
thin = 4,
chains = nchains,
control = list(max_treedepth = 12))
tmp = as.data.frame( summary(fit, 'TFR', probs=c(.10,.25,.50,.75,.90))$summary )
names(tmp) = c('post_mean','se_mean','sd',paste0('Q',c(10,25,50,75,90)),'n_eff','Rhat')
tmp$Code = D$Code[k]
tmp$Year = D$Year[k]
tmp$iTFR = D$iTFR[k]
tmp$lagTFR = D$lagTFR[k]
tmp = dplyr::select(tmp, Code: lagTFR, post_mean, contains('Q'),n_eff,Rhat) %>%
mutate_at(vars(iTFR:Rhat), round, digits=3)
results = rbind( results, tmp)
} # for k## [1] "...starting 1 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.451 seconds (Warm-up)
## Chain 1: 0.433 seconds (Sampling)
## Chain 1: 0.884 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.685 seconds (Warm-up)
## Chain 2: 0.386 seconds (Sampling)
## Chain 2: 1.071 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.502 seconds (Warm-up)
## Chain 3: 0.382 seconds (Sampling)
## Chain 3: 0.884 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.56 seconds (Warm-up)
## Chain 4: 0.327 seconds (Sampling)
## Chain 4: 0.887 seconds (Total)
## Chain 4:
## [1] "...starting 2 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.553 seconds (Warm-up)
## Chain 1: 0.305 seconds (Sampling)
## Chain 1: 0.858 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.641 seconds (Warm-up)
## Chain 2: 0.358 seconds (Sampling)
## Chain 2: 0.999 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.528 seconds (Warm-up)
## Chain 3: 0.353 seconds (Sampling)
## Chain 3: 0.881 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.565 seconds (Warm-up)
## Chain 4: 0.337 seconds (Sampling)
## Chain 4: 0.902 seconds (Total)
## Chain 4:
## [1] "...starting 3 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.656 seconds (Warm-up)
## Chain 1: 0.27 seconds (Sampling)
## Chain 1: 0.926 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.619 seconds (Warm-up)
## Chain 2: 0.349 seconds (Sampling)
## Chain 2: 0.968 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.491 seconds (Warm-up)
## Chain 3: 0.282 seconds (Sampling)
## Chain 3: 0.773 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.531 seconds (Warm-up)
## Chain 4: 0.286 seconds (Sampling)
## Chain 4: 0.817 seconds (Total)
## Chain 4:
## [1] "...starting 4 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.551 seconds (Warm-up)
## Chain 1: 0.342 seconds (Sampling)
## Chain 1: 0.893 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.419 seconds (Warm-up)
## Chain 2: 0.289 seconds (Sampling)
## Chain 2: 0.708 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.435 seconds (Warm-up)
## Chain 3: 0.432 seconds (Sampling)
## Chain 3: 0.867 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.526 seconds (Warm-up)
## Chain 4: 0.381 seconds (Sampling)
## Chain 4: 0.907 seconds (Total)
## Chain 4:
## [1] "...starting 5 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.733 seconds (Warm-up)
## Chain 1: 0.494 seconds (Sampling)
## Chain 1: 1.227 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.63 seconds (Warm-up)
## Chain 2: 0.474 seconds (Sampling)
## Chain 2: 1.104 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.645 seconds (Warm-up)
## Chain 3: 0.412 seconds (Sampling)
## Chain 3: 1.057 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.8 seconds (Warm-up)
## Chain 4: 0.416 seconds (Sampling)
## Chain 4: 1.216 seconds (Total)
## Chain 4:
## [1] "...starting 6 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.536 seconds (Warm-up)
## Chain 1: 0.326 seconds (Sampling)
## Chain 1: 0.862 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.557 seconds (Warm-up)
## Chain 2: 0.509 seconds (Sampling)
## Chain 2: 1.066 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.571 seconds (Warm-up)
## Chain 3: 0.384 seconds (Sampling)
## Chain 3: 0.955 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.494 seconds (Warm-up)
## Chain 4: 0.374 seconds (Sampling)
## Chain 4: 0.868 seconds (Total)
## Chain 4:
## [1] "...starting 7 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.576 seconds (Warm-up)
## Chain 1: 0.574 seconds (Sampling)
## Chain 1: 1.15 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.636 seconds (Warm-up)
## Chain 2: 0.468 seconds (Sampling)
## Chain 2: 1.104 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.624 seconds (Warm-up)
## Chain 3: 0.452 seconds (Sampling)
## Chain 3: 1.076 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.605 seconds (Warm-up)
## Chain 4: 0.381 seconds (Sampling)
## Chain 4: 0.986 seconds (Total)
## Chain 4:
## [1] "...starting 8 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.504 seconds (Warm-up)
## Chain 1: 0.359 seconds (Sampling)
## Chain 1: 0.863 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.612 seconds (Warm-up)
## Chain 2: 0.419 seconds (Sampling)
## Chain 2: 1.031 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.741 seconds (Warm-up)
## Chain 3: 0.424 seconds (Sampling)
## Chain 3: 1.165 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.566 seconds (Warm-up)
## Chain 4: 0.365 seconds (Sampling)
## Chain 4: 0.931 seconds (Total)
## Chain 4:
## [1] "...starting 9 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.465 seconds (Warm-up)
## Chain 1: 0.289 seconds (Sampling)
## Chain 1: 0.754 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.597 seconds (Warm-up)
## Chain 2: 0.255 seconds (Sampling)
## Chain 2: 0.852 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.592 seconds (Warm-up)
## Chain 3: 0.24 seconds (Sampling)
## Chain 3: 0.832 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.607 seconds (Warm-up)
## Chain 4: 0.292 seconds (Sampling)
## Chain 4: 0.899 seconds (Total)
## Chain 4:
## [1] "...starting 10 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.271 seconds (Warm-up)
## Chain 1: 0.152 seconds (Sampling)
## Chain 1: 0.423 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.312 seconds (Warm-up)
## Chain 2: 0.192 seconds (Sampling)
## Chain 2: 0.504 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.338 seconds (Warm-up)
## Chain 3: 0.201 seconds (Sampling)
## Chain 3: 0.539 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.409 seconds (Warm-up)
## Chain 4: 0.191 seconds (Sampling)
## Chain 4: 0.6 seconds (Total)
## Chain 4:
## [1] "...starting 11 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.39 seconds (Warm-up)
## Chain 1: 0.235 seconds (Sampling)
## Chain 1: 0.625 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.316 seconds (Warm-up)
## Chain 2: 0.153 seconds (Sampling)
## Chain 2: 0.469 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.262 seconds (Warm-up)
## Chain 3: 0.154 seconds (Sampling)
## Chain 3: 0.416 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.304 seconds (Warm-up)
## Chain 4: 0.136 seconds (Sampling)
## Chain 4: 0.44 seconds (Total)
## Chain 4:
## [1] "...starting 12 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.324 seconds (Warm-up)
## Chain 1: 0.14 seconds (Sampling)
## Chain 1: 0.464 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.383 seconds (Warm-up)
## Chain 2: 0.16 seconds (Sampling)
## Chain 2: 0.543 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.365 seconds (Warm-up)
## Chain 3: 0.149 seconds (Sampling)
## Chain 3: 0.514 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.332 seconds (Warm-up)
## Chain 4: 0.152 seconds (Sampling)
## Chain 4: 0.484 seconds (Total)
## Chain 4:
## [1] "...starting 13 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.441 seconds (Warm-up)
## Chain 1: 0.25 seconds (Sampling)
## Chain 1: 0.691 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.423 seconds (Warm-up)
## Chain 2: 0.271 seconds (Sampling)
## Chain 2: 0.694 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.448 seconds (Warm-up)
## Chain 3: 0.25 seconds (Sampling)
## Chain 3: 0.698 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.431 seconds (Warm-up)
## Chain 4: 0.291 seconds (Sampling)
## Chain 4: 0.722 seconds (Total)
## Chain 4:
## [1] "...starting 14 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.472 seconds (Warm-up)
## Chain 1: 0.258 seconds (Sampling)
## Chain 1: 0.73 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.455 seconds (Warm-up)
## Chain 2: 0.308 seconds (Sampling)
## Chain 2: 0.763 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.414 seconds (Warm-up)
## Chain 3: 0.27 seconds (Sampling)
## Chain 3: 0.684 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.445 seconds (Warm-up)
## Chain 4: 0.288 seconds (Sampling)
## Chain 4: 0.733 seconds (Total)
## Chain 4:
## [1] "...starting 15 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 2.294 seconds (Warm-up)
## Chain 1: 0.995 seconds (Sampling)
## Chain 1: 3.289 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 2.106 seconds (Warm-up)
## Chain 2: 0.91 seconds (Sampling)
## Chain 2: 3.016 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 2.183 seconds (Warm-up)
## Chain 3: 0.818 seconds (Sampling)
## Chain 3: 3.001 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 2.498 seconds (Warm-up)
## Chain 4: 0.848 seconds (Sampling)
## Chain 4: 3.346 seconds (Total)
## Chain 4:
## [1] "...starting 16 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.447 seconds (Warm-up)
## Chain 1: 0.242 seconds (Sampling)
## Chain 1: 0.689 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.403 seconds (Warm-up)
## Chain 2: 0.344 seconds (Sampling)
## Chain 2: 0.747 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.51 seconds (Warm-up)
## Chain 3: 0.306 seconds (Sampling)
## Chain 3: 0.816 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.456 seconds (Warm-up)
## Chain 4: 0.242 seconds (Sampling)
## Chain 4: 0.698 seconds (Total)
## Chain 4:
## [1] "...starting 17 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.487 seconds (Warm-up)
## Chain 1: 0.281 seconds (Sampling)
## Chain 1: 0.768 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.398 seconds (Warm-up)
## Chain 2: 0.245 seconds (Sampling)
## Chain 2: 0.643 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.397 seconds (Warm-up)
## Chain 3: 0.228 seconds (Sampling)
## Chain 3: 0.625 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.463 seconds (Warm-up)
## Chain 4: 0.276 seconds (Sampling)
## Chain 4: 0.739 seconds (Total)
## Chain 4:
## [1] "...starting 18 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.822 seconds (Warm-up)
## Chain 1: 0.434 seconds (Sampling)
## Chain 1: 1.256 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.753 seconds (Warm-up)
## Chain 2: 0.386 seconds (Sampling)
## Chain 2: 1.139 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.69 seconds (Warm-up)
## Chain 3: 0.369 seconds (Sampling)
## Chain 3: 1.059 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.656 seconds (Warm-up)
## Chain 4: 0.452 seconds (Sampling)
## Chain 4: 1.108 seconds (Total)
## Chain 4:
## [1] "...starting 19 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.516 seconds (Warm-up)
## Chain 1: 0.331 seconds (Sampling)
## Chain 1: 0.847 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.559 seconds (Warm-up)
## Chain 2: 0.255 seconds (Sampling)
## Chain 2: 0.814 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.55 seconds (Warm-up)
## Chain 3: 0.253 seconds (Sampling)
## Chain 3: 0.803 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.609 seconds (Warm-up)
## Chain 4: 0.255 seconds (Sampling)
## Chain 4: 0.864 seconds (Total)
## Chain 4:
## [1] "...starting 20 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.661 seconds (Warm-up)
## Chain 1: 0.618 seconds (Sampling)
## Chain 1: 1.279 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.643 seconds (Warm-up)
## Chain 2: 0.468 seconds (Sampling)
## Chain 2: 1.111 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.73 seconds (Warm-up)
## Chain 3: 0.591 seconds (Sampling)
## Chain 3: 1.321 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0.001 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.749 seconds (Warm-up)
## Chain 4: 0.654 seconds (Sampling)
## Chain 4: 1.403 seconds (Total)
## Chain 4:
## [1] "...starting 21 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.468 seconds (Warm-up)
## Chain 1: 0.281 seconds (Sampling)
## Chain 1: 0.749 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.558 seconds (Warm-up)
## Chain 2: 0.366 seconds (Sampling)
## Chain 2: 0.924 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.562 seconds (Warm-up)
## Chain 3: 0.228 seconds (Sampling)
## Chain 3: 0.79 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.496 seconds (Warm-up)
## Chain 4: 0.302 seconds (Sampling)
## Chain 4: 0.798 seconds (Total)
## Chain 4:
## [1] "...starting 22 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.561 seconds (Warm-up)
## Chain 1: 0.515 seconds (Sampling)
## Chain 1: 1.076 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.549 seconds (Warm-up)
## Chain 2: 0.462 seconds (Sampling)
## Chain 2: 1.011 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.621 seconds (Warm-up)
## Chain 3: 0.468 seconds (Sampling)
## Chain 3: 1.089 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.615 seconds (Warm-up)
## Chain 4: 0.486 seconds (Sampling)
## Chain 4: 1.101 seconds (Total)
## Chain 4:
## [1] "...starting 23 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.597 seconds (Warm-up)
## Chain 1: 0.428 seconds (Sampling)
## Chain 1: 1.025 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.693 seconds (Warm-up)
## Chain 2: 0.537 seconds (Sampling)
## Chain 2: 1.23 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.836 seconds (Warm-up)
## Chain 3: 0.542 seconds (Sampling)
## Chain 3: 1.378 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.632 seconds (Warm-up)
## Chain 4: 0.495 seconds (Sampling)
## Chain 4: 1.127 seconds (Total)
## Chain 4:
## [1] "...starting 24 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.424 seconds (Warm-up)
## Chain 1: 0.235 seconds (Sampling)
## Chain 1: 0.659 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.545 seconds (Warm-up)
## Chain 2: 0.252 seconds (Sampling)
## Chain 2: 0.797 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.587 seconds (Warm-up)
## Chain 3: 0.259 seconds (Sampling)
## Chain 3: 0.846 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.508 seconds (Warm-up)
## Chain 4: 0.239 seconds (Sampling)
## Chain 4: 0.747 seconds (Total)
## Chain 4:
## [1] "...starting 25 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.5 seconds (Warm-up)
## Chain 1: 0.427 seconds (Sampling)
## Chain 1: 0.927 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.423 seconds (Warm-up)
## Chain 2: 0.302 seconds (Sampling)
## Chain 2: 0.725 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.44 seconds (Warm-up)
## Chain 3: 0.456 seconds (Sampling)
## Chain 3: 0.896 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.41 seconds (Warm-up)
## Chain 4: 0.346 seconds (Sampling)
## Chain 4: 0.756 seconds (Total)
## Chain 4:
## [1] "...starting 26 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.871 seconds (Warm-up)
## Chain 1: 0.566 seconds (Sampling)
## Chain 1: 1.437 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.935 seconds (Warm-up)
## Chain 2: 0.808 seconds (Sampling)
## Chain 2: 1.743 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.953 seconds (Warm-up)
## Chain 3: 0.55 seconds (Sampling)
## Chain 3: 1.503 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.768 seconds (Warm-up)
## Chain 4: 0.544 seconds (Sampling)
## Chain 4: 1.312 seconds (Total)
## Chain 4:
## [1] "...starting 27 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.943 seconds (Warm-up)
## Chain 1: 0.611 seconds (Sampling)
## Chain 1: 1.554 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.965 seconds (Warm-up)
## Chain 2: 0.53 seconds (Sampling)
## Chain 2: 1.495 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.995 seconds (Warm-up)
## Chain 3: 0.668 seconds (Sampling)
## Chain 3: 1.663 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.763 seconds (Warm-up)
## Chain 4: 0.557 seconds (Sampling)
## Chain 4: 1.32 seconds (Total)
## Chain 4:
## [1] "...starting 28 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.524 seconds (Warm-up)
## Chain 1: 0.354 seconds (Sampling)
## Chain 1: 0.878 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.63 seconds (Warm-up)
## Chain 2: 0.426 seconds (Sampling)
## Chain 2: 1.056 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.508 seconds (Warm-up)
## Chain 3: 0.401 seconds (Sampling)
## Chain 3: 0.909 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.591 seconds (Warm-up)
## Chain 4: 0.457 seconds (Sampling)
## Chain 4: 1.048 seconds (Total)
## Chain 4:
## [1] "...starting 29 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.603 seconds (Warm-up)
## Chain 1: 0.309 seconds (Sampling)
## Chain 1: 0.912 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.558 seconds (Warm-up)
## Chain 2: 0.285 seconds (Sampling)
## Chain 2: 0.843 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.675 seconds (Warm-up)
## Chain 3: 0.33 seconds (Sampling)
## Chain 3: 1.005 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0.001 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.612 seconds (Warm-up)
## Chain 4: 0.513 seconds (Sampling)
## Chain 4: 1.125 seconds (Total)
## Chain 4:
## [1] "...starting 30 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.386 seconds (Warm-up)
## Chain 1: 0.21 seconds (Sampling)
## Chain 1: 0.596 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.485 seconds (Warm-up)
## Chain 2: 0.227 seconds (Sampling)
## Chain 2: 0.712 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.486 seconds (Warm-up)
## Chain 3: 0.251 seconds (Sampling)
## Chain 3: 0.737 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.423 seconds (Warm-up)
## Chain 4: 0.159 seconds (Sampling)
## Chain 4: 0.582 seconds (Total)
## Chain 4:
## [1] "...starting 31 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.477 seconds (Warm-up)
## Chain 1: 0.397 seconds (Sampling)
## Chain 1: 0.874 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.573 seconds (Warm-up)
## Chain 2: 0.395 seconds (Sampling)
## Chain 2: 0.968 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0.001 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.465 seconds (Warm-up)
## Chain 3: 0.492 seconds (Sampling)
## Chain 3: 0.957 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.527 seconds (Warm-up)
## Chain 4: 0.417 seconds (Sampling)
## Chain 4: 0.944 seconds (Total)
## Chain 4:
## [1] "...starting 32 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.552 seconds (Warm-up)
## Chain 1: 0.28 seconds (Sampling)
## Chain 1: 0.832 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0.001 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.611 seconds (Warm-up)
## Chain 2: 0.372 seconds (Sampling)
## Chain 2: 0.983 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.696 seconds (Warm-up)
## Chain 3: 0.265 seconds (Sampling)
## Chain 3: 0.961 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.587 seconds (Warm-up)
## Chain 4: 0.332 seconds (Sampling)
## Chain 4: 0.919 seconds (Total)
## Chain 4:
## [1] "...starting 33 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.579 seconds (Warm-up)
## Chain 1: 0.348 seconds (Sampling)
## Chain 1: 0.927 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.548 seconds (Warm-up)
## Chain 2: 0.314 seconds (Sampling)
## Chain 2: 0.862 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.613 seconds (Warm-up)
## Chain 3: 0.412 seconds (Sampling)
## Chain 3: 1.025 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.42 seconds (Warm-up)
## Chain 4: 0.397 seconds (Sampling)
## Chain 4: 0.817 seconds (Total)
## Chain 4:
## [1] "...starting 34 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.554 seconds (Warm-up)
## Chain 1: 0.274 seconds (Sampling)
## Chain 1: 0.828 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.45 seconds (Warm-up)
## Chain 2: 0.239 seconds (Sampling)
## Chain 2: 0.689 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.493 seconds (Warm-up)
## Chain 3: 0.317 seconds (Sampling)
## Chain 3: 0.81 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.44 seconds (Warm-up)
## Chain 4: 0.287 seconds (Sampling)
## Chain 4: 0.727 seconds (Total)
## Chain 4:
## [1] "...starting 35 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.518 seconds (Warm-up)
## Chain 1: 0.244 seconds (Sampling)
## Chain 1: 0.762 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.551 seconds (Warm-up)
## Chain 2: 0.31 seconds (Sampling)
## Chain 2: 0.861 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.502 seconds (Warm-up)
## Chain 3: 0.261 seconds (Sampling)
## Chain 3: 0.763 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.638 seconds (Warm-up)
## Chain 4: 0.284 seconds (Sampling)
## Chain 4: 0.922 seconds (Total)
## Chain 4:
## [1] "...starting 36 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0.001 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.58 seconds (Warm-up)
## Chain 1: 0.306 seconds (Sampling)
## Chain 1: 0.886 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.463 seconds (Warm-up)
## Chain 2: 0.373 seconds (Sampling)
## Chain 2: 0.836 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.458 seconds (Warm-up)
## Chain 3: 0.344 seconds (Sampling)
## Chain 3: 0.802 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.544 seconds (Warm-up)
## Chain 4: 0.285 seconds (Sampling)
## Chain 4: 0.829 seconds (Total)
## Chain 4:
## [1] "...starting 37 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.43 seconds (Warm-up)
## Chain 1: 0.272 seconds (Sampling)
## Chain 1: 0.702 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.472 seconds (Warm-up)
## Chain 2: 0.307 seconds (Sampling)
## Chain 2: 0.779 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.439 seconds (Warm-up)
## Chain 3: 0.304 seconds (Sampling)
## Chain 3: 0.743 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.499 seconds (Warm-up)
## Chain 4: 0.364 seconds (Sampling)
## Chain 4: 0.863 seconds (Total)
## Chain 4:
## [1] "...starting 38 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.704 seconds (Warm-up)
## Chain 1: 0.436 seconds (Sampling)
## Chain 1: 1.14 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.714 seconds (Warm-up)
## Chain 2: 0.372 seconds (Sampling)
## Chain 2: 1.086 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.746 seconds (Warm-up)
## Chain 3: 0.49 seconds (Sampling)
## Chain 3: 1.236 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.862 seconds (Warm-up)
## Chain 4: 0.512 seconds (Sampling)
## Chain 4: 1.374 seconds (Total)
## Chain 4:
## [1] "...starting 39 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.416 seconds (Warm-up)
## Chain 1: 0.327 seconds (Sampling)
## Chain 1: 0.743 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.413 seconds (Warm-up)
## Chain 2: 0.243 seconds (Sampling)
## Chain 2: 0.656 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.409 seconds (Warm-up)
## Chain 3: 0.296 seconds (Sampling)
## Chain 3: 0.705 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.477 seconds (Warm-up)
## Chain 4: 0.325 seconds (Sampling)
## Chain 4: 0.802 seconds (Total)
## Chain 4:
## [1] "...starting 40 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.607 seconds (Warm-up)
## Chain 1: 0.336 seconds (Sampling)
## Chain 1: 0.943 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.631 seconds (Warm-up)
## Chain 2: 0.28 seconds (Sampling)
## Chain 2: 0.911 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.611 seconds (Warm-up)
## Chain 3: 0.298 seconds (Sampling)
## Chain 3: 0.909 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0.001 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 10 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.553 seconds (Warm-up)
## Chain 4: 0.321 seconds (Sampling)
## Chain 4: 0.874 seconds (Total)
## Chain 4:
## [1] "...starting 41 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.488 seconds (Warm-up)
## Chain 1: 0.268 seconds (Sampling)
## Chain 1: 0.756 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.38 seconds (Warm-up)
## Chain 2: 0.236 seconds (Sampling)
## Chain 2: 0.616 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.459 seconds (Warm-up)
## Chain 3: 0.259 seconds (Sampling)
## Chain 3: 0.718 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.496 seconds (Warm-up)
## Chain 4: 0.252 seconds (Sampling)
## Chain 4: 0.748 seconds (Total)
## Chain 4:
## [1] "...starting 42 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.448 seconds (Warm-up)
## Chain 1: 0.316 seconds (Sampling)
## Chain 1: 0.764 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.412 seconds (Warm-up)
## Chain 2: 0.253 seconds (Sampling)
## Chain 2: 0.665 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.429 seconds (Warm-up)
## Chain 3: 0.353 seconds (Sampling)
## Chain 3: 0.782 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.476 seconds (Warm-up)
## Chain 4: 0.365 seconds (Sampling)
## Chain 4: 0.841 seconds (Total)
## Chain 4:
## [1] "...starting 43 of 43"
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 1).
## Chain 1:
## Chain 1: Gradient evaluation took 0 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1:
## Chain 1:
## Chain 1: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 1: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 1: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 1: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 1: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 1: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 1: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 1: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 1: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 1: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 1: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 1: Iteration: 900 / 900 [100%] (Sampling)
## Chain 1:
## Chain 1: Elapsed Time: 0.409 seconds (Warm-up)
## Chain 1: 0.219 seconds (Sampling)
## Chain 1: 0.628 seconds (Total)
## Chain 1:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 2).
## Chain 2:
## Chain 2: Gradient evaluation took 0 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2:
## Chain 2:
## Chain 2: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 2: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 2: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 2: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 2: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 2: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 2: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 2: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 2: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 2: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 2: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 2: Iteration: 900 / 900 [100%] (Sampling)
## Chain 2:
## Chain 2: Elapsed Time: 0.375 seconds (Warm-up)
## Chain 2: 0.243 seconds (Sampling)
## Chain 2: 0.618 seconds (Total)
## Chain 2:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 3).
## Chain 3:
## Chain 3: Gradient evaluation took 0 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3:
## Chain 3:
## Chain 3: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 3: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 3: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 3: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 3: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 3: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 3: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 3: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 3: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 3: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 3: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 3: Iteration: 900 / 900 [100%] (Sampling)
## Chain 3:
## Chain 3: Elapsed Time: 0.457 seconds (Warm-up)
## Chain 3: 0.217 seconds (Sampling)
## Chain 3: 0.674 seconds (Total)
## Chain 3:
##
## SAMPLING FOR MODEL 'single schedule TFR' NOW (CHAIN 4).
## Chain 4:
## Chain 4: Gradient evaluation took 0 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4:
## Chain 4:
## Chain 4: Iteration: 1 / 900 [ 0%] (Warmup)
## Chain 4: Iteration: 90 / 900 [ 10%] (Warmup)
## Chain 4: Iteration: 180 / 900 [ 20%] (Warmup)
## Chain 4: Iteration: 270 / 900 [ 30%] (Warmup)
## Chain 4: Iteration: 301 / 900 [ 33%] (Sampling)
## Chain 4: Iteration: 390 / 900 [ 43%] (Sampling)
## Chain 4: Iteration: 480 / 900 [ 53%] (Sampling)
## Chain 4: Iteration: 570 / 900 [ 63%] (Sampling)
## Chain 4: Iteration: 660 / 900 [ 73%] (Sampling)
## Chain 4: Iteration: 750 / 900 [ 83%] (Sampling)
## Chain 4: Iteration: 840 / 900 [ 93%] (Sampling)
## Chain 4: Iteration: 900 / 900 [100%] (Sampling)
## Chain 4:
## Chain 4: Elapsed Time: 0.395 seconds (Warm-up)
## Chain 4: 0.218 seconds (Sampling)
## Chain 4: 0.613 seconds (Total)
## Chain 4:rownames(results) = NULL
results## Code Year iTFR lagTFR post_mean Q10 Q25 Q50 Q75 Q90 n_eff
## 1 BF 2003 5.317 5.9 6.194 5.477 5.796 6.154 6.504 6.967 596.086
## 2 BF 2010 5.736 6.0 5.993 5.494 5.708 5.971 6.238 6.576 559.524
## 3 BJ 2006 5.729 5.7 5.715 5.282 5.444 5.672 5.943 6.197 502.184
## 4 CD 2007 5.609 6.3 6.154 5.454 5.767 6.114 6.467 6.800 318.825
## 5 CD 2013 6.327 6.6 6.414 5.861 6.084 6.364 6.706 7.033 614.524
## 6 CM 2004 4.778 5.0 5.357 4.779 5.016 5.329 5.664 6.012 533.655
## 7 CM 2011 4.864 5.1 5.256 4.751 4.978 5.219 5.527 5.812 507.039
## 8 ET 2005 5.029 5.4 5.459 4.983 5.170 5.422 5.705 5.989 685.377
## 9 ET 2016 4.650 4.6 4.554 4.218 4.349 4.500 4.704 4.907 90.205
## 10 GH 2003 4.108 4.4 4.347 4.039 4.165 4.339 4.513 4.666 579.796
## 11 GH 2008 3.889 4.0 4.041 3.751 3.879 4.027 4.188 4.357 606.727
## 12 GH 2014 4.046 4.2 3.990 3.789 3.880 3.976 4.082 4.200 481.796
## 13 GN 2005 4.970 5.7 5.643 5.248 5.373 5.590 5.830 6.106 564.597
## 14 GN 2012 4.937 5.1 5.367 4.871 5.092 5.329 5.585 5.919 442.129
## 15 IA 2015 2.391 2.2 2.403 2.286 2.340 2.397 2.460 2.519 547.349
## 16 KE 2003 4.749 4.9 5.041 4.583 4.798 5.041 5.288 5.477 531.716
## 17 KE 2008 4.544 4.6 4.585 4.209 4.388 4.556 4.765 4.994 543.902
## 18 KE 2014 4.212 3.9 3.995 3.740 3.846 3.966 4.097 4.267 207.103
## 19 MD 2008 4.825 4.8 5.057 4.749 4.887 5.043 5.208 5.385 636.219
## 20 ML 2006 6.011 6.6 6.847 6.136 6.388 6.759 7.203 7.683 547.480
## 21 ML 2012 6.484 6.1 6.241 5.819 5.989 6.198 6.450 6.685 488.564
## 22 MW 2004 5.850 6.0 6.175 5.477 5.783 6.116 6.538 6.857 610.121
## 23 MW 2010 5.477 5.7 5.594 5.053 5.295 5.538 5.854 6.165 503.429
## 24 MZ 2011 5.518 5.9 5.781 5.339 5.528 5.751 6.009 6.269 466.269
## 25 NG 2003 4.910 5.7 5.764 5.065 5.316 5.690 6.145 6.600 484.395
## 26 NG 2008 5.237 5.7 5.655 5.163 5.334 5.627 5.933 6.227 593.564
## 27 NG 2013 5.203 5.5 5.511 5.096 5.257 5.490 5.719 5.969 574.412
## 28 NI 2006 6.624 7.0 7.253 6.490 6.764 7.164 7.656 8.202 531.567
## 29 NI 2012 7.695 7.6 7.525 6.958 7.177 7.449 7.810 8.171 500.890
## 30 PK 2006 3.813 4.1 5.427 5.140 5.264 5.398 5.582 5.758 551.549
## 31 RW 2005 4.821 6.1 5.500 4.947 5.164 5.462 5.782 6.116 610.172
## 32 RW 2010 4.406 4.6 4.481 4.080 4.264 4.473 4.684 4.866 468.289
## 33 TZ 2004 5.405 5.7 5.580 5.074 5.306 5.543 5.805 6.129 490.222
## 34 TZ 2010 5.293 5.4 5.452 5.032 5.222 5.427 5.669 5.874 599.188
## 35 TZ 2015 5.023 5.2 5.188 4.812 4.985 5.166 5.382 5.593 574.410
## 36 UG 2006 6.289 6.7 6.769 6.149 6.410 6.735 7.089 7.443 596.857
## 37 UG 2011 6.081 6.2 6.301 5.764 6.015 6.262 6.574 6.873 533.982
## 38 UG 2016 5.482 5.4 5.565 5.126 5.297 5.558 5.797 6.045 496.495
## 39 ZM 2007 5.741 6.2 5.889 5.303 5.571 5.876 6.179 6.480 576.756
## 40 ZM 2013 5.389 5.3 5.353 4.982 5.156 5.326 5.529 5.749 543.139
## 41 ZW 2005 3.828 3.8 4.023 3.618 3.810 4.012 4.212 4.442 588.421
## 42 ZW 2010 3.975 4.1 3.957 3.612 3.751 3.933 4.136 4.339 450.463
## 43 ZW 2015 4.258 4.0 4.222 3.966 4.069 4.201 4.360 4.513 504.274
## Rhat
## 1 1.003
## 2 1.004
## 3 1.000
## 4 1.006
## 5 0.995
## 6 1.002
## 7 1.000
## 8 0.998
## 9 1.038
## 10 0.995
## 11 0.996
## 12 0.997
## 13 0.999
## 14 0.997
## 15 1.006
## 16 1.002
## 17 0.997
## 18 1.021
## 19 0.997
## 20 1.000
## 21 1.003
## 22 1.004
## 23 1.005
## 24 1.004
## 25 0.999
## 26 0.997
## 27 1.000
## 28 1.004
## 29 1.000
## 30 0.997
## 31 1.002
## 32 1.000
## 33 1.003
## 34 1.007
## 35 0.998
## 36 0.998
## 37 0.995
## 38 1.009
## 39 0.997
## 40 0.997
## 41 0.999
## 42 1.003
## 43 0.997# write.csv(results, "../R/DATA-PROCESSED/IPUMS-bayesitfr.csv")Loading in the Non-Human data
# Importing the Bronikowski primate data.
PRIM_DATA <- read_csv("../R/DATA-RAW/PRIMATES-Bronikowski.LifeTables.SciData2016.csv")
# Importing the lion data from Jones et al
need_lions = FALSE # FALSE once downloaded successfully (2 Mar 2019)
if (need_lions) {
download.file(url ="https://media.nature.com/original/nature-assets/nature/journal/v505/n7482/source_data/nature12789-f1.xls",
destfile="../R/DATA-RAW/PRIMATES-nature12789-f1.xls", mode = "wb")
}
# Processing the Jones data
jones <- read_excel("../R/DATA-RAW/PRIMATES-nature12789-f1.xls", sheet = 37) %>%
filter(!Lion == "x")
names(jones)[c(1,3,6)] = c('Age','N.x.female','nFx')
jones = jones %>%
mutate(Species = "African Lion", #setting the species
Age = as.numeric(Age),
N.x.female = as.numeric(N.x.female),
N.x.male = 0, #creating some columns to allow a clean rbind with the PRIM_DATA file
fertint = ifelse(nFx == 0, 0, 1), # making the fertility interval length
child = 0,
nFx = as.numeric(nFx),
Breeding_females = 0,
N.x.male = 0,
Offspring = 0,
fertstart = min(Age[which(nFx>0)]),
fertend = max(Age[which(nFx>0)]),
fertlength = as.numeric(fertend) - as.numeric(fertstart)) %>%
dplyr::select(Age, N.x.female, nFx, Species, N.x.male, fertint, child, Breeding_females, Offspring, fertstart, fertend, fertlength) #selecting the columns for a clean rbind with PRIM_DATA
# Data come from various sources and are listed in the main text and supplementary materials.
prim2 <- tribble(
~'Species', ~'AGE', ~'Maleenter', ~'MaleDie', ~'FemaleEnter', ~'FemaleDie', ~'nFx',
'Thomas Langur', 0, 50, 24, 61, 26, 0,
'Thomas Langur', 1, 0, 0, 34, 9, 0,
'Thomas Langur', 2, 0, 0, 21, 2, 0,
'Thomas Langur', 3, 0, 0, 15, 3, 0,
'Thomas Langur', 4, 0, 0, 13, 1, 0.26,
'Thomas Langur', 5, 0, 0, 276, 15, 0.32,
'Thomas Langur', 6, 0, 0, 0, 0, 0.65,
'Thomas Langur', 7, 0, 0, 0, 0, 0.49,
'Thomas Langur', 8, 0, 0, 0, 0, 0.48,
'Thomas Langur', 9, 0, 0, 0, 0, 0.41,
'Thomas Langur', 10, 0, 0, 0, 0, 0.48,
'Thomas Langur', 11, 0, 0, 0, 0, 0.58,
'Macaque', 0, 0, 0, 2368, 0, 0,
'Macaque', 1, 0, 0, 1919.9, 0, 0,
'Macaque', 2, 0, 0, 1569.4, 0, 0,
'Macaque', 3, 0, 0, 1319.1, 0, 0.0765673565309681,
'Macaque', 4, 0, 0, 1122.3, 0, 0.529270248596632,
'Macaque', 5, 0, 0, 978.4, 0, 0.603025347506132,
'Macaque', 6, 0, 0, 841.7, 0, 0.577402875133658,
'Macaque', 7, 0, 0, 689.6, 0, 0.587296983758701,
'Macaque', 8, 0, 0, 565, 0, 0.527433628318584,
'Macaque', 9, 0, 0, 463.9, 0, 0.48286268592369,
'Macaque', 10, 0, 0, 361.9, 0, 0.530533296490743,
'Macaque', 11, 0, 0, 288.6, 0, 0.488565488565489,
'Macaque', 12, 0, 0, 232.4, 0, 0.430292598967298,
'Macaque', 13, 0, 0, 184, 0, 0.385869565217391,
'Macaque', 14, 0, 0, 134.3, 0, 0.275502606105733,
'Macaque', 15, 0, 0, 99.3, 0, 0.392749244712991,
'Macaque', 16, 0, 0, 74.8, 0, 0.200534759358289,
'Macaque', 17, 0, 0, 52, 0, 0.230769230769231,
'Macaque', 18, 0, 0, 38, 0, 0.0789473684210526,
'Macaque', 19, 0, 0, 21.3, 0, 0.0938967136150235,
'Macaque', 20, 0, 0, 12.6, 0, 0.158730158730159,
'Macaque', 21, 0, 0, 8.1, 0, 0.123456790123457,
'Macaque', 22, 0, 0, 7.2, 0, 0.138888888888889,
'Macaque', 23, 0, 0, 4.8, 0, 0,
'Macaque', 24, 0, 0, 3.8, 0, 0,
'Macaque', 25, 0, 0, 2.2, 0, 0,
'Macaque', 26, 0, 0, 2, 0, 0,
'Macaque', 27, 0, 0, 1.8, 0, 0,
'Macaque', 28, 0, 0, 1, 0, 0,
'Macaque', 29, 0, 0, 0.2, 0, 0,
'Northern Fur Seal', 0, 0, 0, 0, 2096, 0,
'Northern Fur Seal', 1, 0, 0, 0, 0, 0,
'Northern Fur Seal', 2, 0, 0, 0, 0, 0,
'Northern Fur Seal', 3, 0, 0, 0, 646, 0.015,
'Northern Fur Seal', 4, 0, 0, 0, 572, 0.22,
'Northern Fur Seal', 5, 0, 0, 0, 530, 0.395,
'Northern Fur Seal', 6, 0, 0, 0, 505, 0.395,
'Northern Fur Seal', 7, 0, 0, 0, 486, 0.425,
'Northern Fur Seal', 8, 0, 0, 0, 478, 0.46,
'Northern Fur Seal', 9, 0, 0, 0, 447, 0.445,
'Northern Fur Seal', 10, 0, 0, 0, 434, 0.45,
'Northern Fur Seal', 11, 0, 0, 0, 429, 0.44,
'Northern Fur Seal', 12, 0, 0, 0, 387, 0.43,
'Northern Fur Seal', 13, 0, 0, 0, 362, 0.42,
'Northern Fur Seal', 14, 0, 0, 0, 336, 0.41,
'Northern Fur Seal', 15, 0, 0, 0, 293, 0.39,
'Northern Fur Seal', 16, 0, 0, 0, 233, 0.33,
'Northern Fur Seal', 17, 0, 0, 0, 142, 0.355,
'Northern Fur Seal', 18, 0, 0, 0, 97, 0.265,
'Northern Fur Seal', 19, 0, 0, 0, 59, 0.255
)
prim2tfr <- prim2 %>%
group_by(Species) %>%
summarise(TFR_table = sum(nFx))
prim2children <- prim2 %>%
filter(AGE == 0) %>%
mutate(child = Maleenter + MaleDie + FemaleEnter + FemaleDie) %>%
dplyr::select(Species, child)
prim2women <- prim2 %>%
group_by(Species) %>%
mutate(fertint = ifelse(nFx == 0, 0, 1),
fertstart = min(AGE[which(nFx>0)]),
fertend = max(AGE[which(nFx>0)]),
fertlength = as.numeric(fertend) - as.numeric(fertstart)) %>%
summarise(Women = sum(as.numeric(FemaleEnter[which(AGE >= fertstart & AGE<=fertend)])) + sum(as.numeric(FemaleDie[which(AGE >= fertstart & AGE<=fertend)])),
fertlength = unique(fertlength),
fertstart = unique(fertstart),
fertend = unique(fertend))
prim22 <- left_join(prim2children, prim2women) %>%
left_join(., prim2tfr)
# Calculating the total number of women, the total number of children, and the width of the fertility interval for the lions
lion <- jones %>%
group_by(Species) %>%
summarise(Women = sum(as.numeric(N.x.female[which(Age>= fertstart & Age<=fertend)])),
child = sum(as.numeric(N.x.female[Age ==0])),
fertlength = unique(fertlength),
fertstart = unique(fertstart),
fertend = unique(fertend))
# subsetting the PRIM_DATA to exclude Sifaka. summing the total number of children, estimating nFx
d <- PRIM_DATA %>%
group_by(Species) %>%
mutate(child = N.x.female + N.x.male + N.x.unknown,
nFx = Offspring / Breeding_females,
nFx = ifelse(is.na(nFx),0, nFx),
fertstart = min(Age[which(nFx>0)]),
fertend = max(Age[which(nFx>0)]),
fertlength = fertend - fertstart)
# Selecting the number of children from the Primate data
children <- d %>%
filter(Age == 0) %>%
dplyr::select(Species, child)
# Summing the number of child-bearing Women and the fertility interval by species for the primate data.
women <- d %>%
group_by(Species) %>%
summarize(Women = sum(N.x.female[which(Age>= fertstart & Age<=fertend)]),
fertlength = unique(fertlength),
fertstart = unique(fertstart),
fertend = unique(fertend))
# rbinding the primate data and the lion data. Summing the nFx values to arrive at a TFR
TFR_table <- bind_rows(d, jones) %>%
group_by(Species) %>%
summarise(TFR_table = sum(as.numeric(nFx)))
# joining the child/women data from the primates. Then rbinding it with the lion data
cw <- inner_join(children, women) %>%
bind_rows(., lion)
# Joining the child/woman data with the oTFR data. Calculating the iTFR
combined <- left_join(cw, TFR_table) %>%
bind_rows(., prim22) %>%
mutate(iTFR = (child/Women) * fertlength)Loading in the US County data
# Importing the Natality files from CDC Wonder for US Counties, 2007-2010 ###
tfr_county0710 <- read_tsv("../R/DATA-RAW/USCounties/USCOUNTY-Natality, 2007-2010.txt") %>%
dplyr::select(County, CountyCode, AgeofMother9Code, Year, Births, FemalePopulation) %>% # selecting specific values
dplyr::mutate(YearCode = as.numeric(Year)) # Year is sometimes weird, this converts it to numeric
# Importing the Natality file from CDC Wonder for US Counties, 2006-2010 ###
tfr_county06 <- read_tsv("../R/DATA-RAW/USCounties/USCOUNTY-Natality, 2003-2006.txt")%>%
dplyr::select(County, CountyCode, AgeofMother9Code, Year, Births, FemalePopulation) %>%
dplyr::mutate(YearCode = as.numeric(Year)*1)
# Merging the two Natality files together ###
tfr_county <- full_join(tfr_county06, tfr_county0710) %>%
dplyr::filter(!is.na(County)) %>% # dropping all of the extra stuff at the bottom of the CDC's output
group_by(County, CountyCode, Year) %>%
dplyr::mutate(fertrat = (Births / as.numeric(FemalePopulation))*5) %>% # Calculating ASFRs
dplyr::summarize(TFR = sum(na.omit(fertrat))) # Calculating the TFR
# Calculating the lagged TFR values
tfr_county$lagTFR = NA
for (this.county in unique(tfr_county$CountyCode)) {
ix = which(tfr_county$CountyCode == this.county)
tfr_county$lagTFR[ix] = mean_lag5( tfr_county$TFR[ix])
}
# Downloading the IHME data on e0 for US counties.
# need_county_e0 = FALSE # FALSE once successfully downloaded (02 Mar 2019)
# if (need_county_e0) {
# download.file("http://ghdx.healthdata.org/sites/default/files/record-attached-files/IHME_USA_COUNTY_LE_MORTALITY_RISK_1980_2014_NATIONAL_XLSX.zip",
# "../R/DATA-RAW/USCounties/USCOUNTY-ihme0.zip")
# unzip(zipfile='../R/DATA-RAW/USCounties/USCOUNTY-ihme0.zip', exdir = "DATA-RAW")
# }
# Processing the IHME data - edited 01 Mar 2019 (file changes at healthdata.org?)
countye0 <- read_excel("../R/DATA-RAW/USCounties/IHME_USA_COUNTY_LE_MORTALITY_RISK_1980_2014_NATIONAL_Y2017M05D08.xlsx",
sheet = 1, skip=1, col_names =TRUE) %>%
dplyr::select(FIPS,ex=9) %>% # FIPS code and 2010 e0 values like 78.82 (78.81, 78.84)
separate(ex, c("ex", "drop"), sep = " " ) %>%
dplyr::mutate(CountyCode = str_pad(trimws(FIPS), 5, pad = "0"),
ex = as.numeric(ex)) %>%
dplyr::select(-drop)
# Importing the Census 2010 information for US Counties
census_county <- read_csv("../R/DATA-RAW/USCounties/USCENSUS-county2010.csv") %>%
dplyr::mutate(W = (W1517 + W1819 + W20 + W21 + W2224 + W2529 + W3034 + W3539 + W4044 + W4549), # estimating total number of Women
CWR = (m0004 + W0004) / W, # estimating Child-woman ratio
p2534 = (W2529 + W3034) / W, # estimating the proportion of women aged 25-34
xTFR = (coef(reg)[1] + coef(reg)[2] * p2534) * CWR, # applying the regression coefficients from the HMD/HFD to US counties
iTFR = CWR*7,
CountyCode = sprintf("%05d", KEY),
Year = 2010) %>%
left_join(., tfr_county, by = c("CountyCode", "Year")) %>%
left_join(., countye0, by = "CountyCode") %>%
dplyr::mutate(e0 = plyr::round_any(ex, 10, floor)) %>%
left_join(., relecoefficients) %>%
dplyr::mutate(eadj = ex-e0,
eadja = alpha + eadj*deltaa,
eadjb = beta + eadj*deltab,
rele = (1+1.05)*(eadja+(eadjb*(CWR)))) %>%
dplyr::select(CountyCode, xTFR, iTFR, rele, lagTFR, Year)
# Estimating the 50th percentile error rate from the xTFR method
countyeval <- census_county %>%
dplyr::mutate(num = if_else(lagTFR >0,1,0)) %>%
dplyr::summarize(tot = sum(num, na.rm = T) ,
xlagTFR50 = quantile(abs(xTFR / lagTFR -1), 0.5, na.rm=T)*100,
xlagTFR90 = quantile(abs(xTFR / lagTFR -1), 0.9, na.rm=T)*100,
xlagTFR_abs50 = quantile(abs(xTFR - lagTFR), 0.5, na.rm=T),
xlagTFR_abs90 = quantile(abs(xTFR - lagTFR), 0.9, na.rm=T),
ilagTFR50 = quantile(abs(iTFR / lagTFR -1), 0.5, na.rm=T)*100,
ilagTFR90 = quantile(abs(iTFR / lagTFR -1), 0.9, na.rm=T)*100,
ilagTFR_abs50 = quantile(abs(iTFR - lagTFR), 0.5, na.rm=T),
ilagTFR_abs90 = quantile(abs(iTFR - lagTFR), 0.9, na.rm=T),
rlagTFR50 = quantile(abs(rele / lagTFR -1), 0.5, na.rm=T)*100,
rlagTFR90 = quantile(abs(rele / lagTFR -1), 0.9, na.rm=T)*100,
rlagTFR_abs50 = quantile(abs(rele - lagTFR), 0.5, na.rm=T),
rlagTFR_abs90 = quantile(abs(rele - lagTFR), 0.9, na.rm=T))
# Selecting the lagged TFR from the 5-year time series for merging with the shapefile.
selectcnties <- census_county %>%
filter(!is.na(lagTFR))Assembling Error summaries over all methods
# DHS and HFD/HMD error summaries
part1 = big %>%
dplyr::select(-q5) %>%
gather(key=Method, value=estimate,-Code,-Year,-lagTFR, -source, -C ) %>%
mutate(err=estimate-lagTFR,
ape= 100* abs(err)/lagTFR ) %>%
filter( is.finite(ape)) %>%
dplyr::select(Data=source, Method, ape, err, lagTFR)
# census county error summaries
part2 = census_county %>%
gather(key=Method, value=estimate,-CountyCode,-Year,-lagTFR ) %>%
mutate(source='US counties',
err=estimate-lagTFR,
ape= 100* abs(err)/lagTFR ) %>%
filter( is.finite(ape)) %>%
dplyr::select(Data=source, Method, ape, err, lagTFR)
parts = rbind(part1,part2) %>%
group_by(Data,Method) %>%
summarize(n = n(),
Q10 = quantile(ape,.10),
Q50 = quantile(ape,.50),
Q90 = quantile(ape,.90),
A10 = quantile(abs(err) ,.10),
A50 = quantile(abs(err), .50),
A90 = quantile(abs(err), .90)) %>%
ungroup()
whole = rbind(part1,part2) %>%
group_by(Method) %>%
summarize(n=n(),
Q10 = quantile(ape,.10),
Q50 = quantile(ape,.50),
Q90 = quantile(ape,.90),
A10 = quantile(abs(err),.10),
A50 = quantile(abs(err),.50),
A90 = quantile(abs(err),.90)) %>%
mutate(Data='All Data') %>%
ungroup() %>%
dplyr::select(Data,Method,n,Q10:A90)
allerrortable_hfddhs <- big %>%
dplyr::select(-C,-W,-q5) %>%
gather(key=Method, value=estimate,-Code,-Year,-lagTFR, -source ) %>%
mutate(err=estimate-lagTFR,
ape= abs(err)/lagTFR) %>%
filter( is.finite(ape)) %>%
dplyr::select(Data=source, Method, ape, err)
allerrortable_county <- census_county %>%
gather(key=Method, value=estimate,-CountyCode,-Year,-lagTFR ) %>%
mutate(source='US counties',
err=estimate-lagTFR,
ape= abs(err)/lagTFR) %>%
filter( is.finite(ape)) %>%
dplyr::select(Data=source, Method, ape, err)
allerrortable <- rbind(allerrortable_county, allerrortable_hfddhs) %>%
filter(!Method == "rele") %>%
mutate(Method =
factor(Method,
levels=c('iTFR','iTFR+','xTFR','xTFR+','bTFR','rele'),
labels=c('iTFR','iTFR+','xTFR','xTFR+','bTFR','Rele'),
ordered=TRUE
)) %>%
group_by(Data, Method) %>%
dplyr::summarise(n = n(),
`50%ile Absolute Error` = f_num(quantile(abs(err), 0.5),2, "0"),
`90%ile Absolute Error` = f_num(quantile(abs(err), 0.9), 2, "0"),
`50%ile APE` = f_prop2percent(quantile(ape, 0.5),1),
`90%ile APE` = f_prop2percent(quantile(ape, 0.9),1)) %>%
ungroup() %>%
rename("Method Family" = "Method") Analysis of s versus qx
# calculate correlation of s=5L0/5 with
# 1/(1-qx_const*q5) in Swedish historical data
# qx_const probably = 0.75
SWE = read.table('../R/DATA-RAW/SWE_fltper_1x1.txt', skip=2, header=TRUE, stringsAsFactors = FALSE)
# replace Age with numeric
SWE$Age = 0:110
radix = 100000
SWE = SWE %>%
filter(Age < 5) %>%
group_by(Year) %>%
summarize(s_obs = sum(Lx)/(5*radix),
q5 = 1-lx[5]/radix,
s_approx = 1-.75*q5)
(s_corr = cor(SWE$s_obs, SWE$s_approx ))## [1] 0.9993964(s_min = min(SWE$s_obs))## [1] 0.660902(s_min_year = SWE$Year[which.min(SWE$s_obs)])## [1] 1773(s_max = max(SWE$s_obs))## [1] 0.998046(s_max_year = SWE$Year[which.max(SWE$s_obs)])## [1] 2014(s_error = (1/SWE$s_approx) / (1/SWE$s_obs))## [1] 0.9754617 0.9742012 0.9759557 0.9729831 0.9687790 0.9713851 0.9780043
## [8] 0.9751293 0.9743604 0.9714847 0.9710779 0.9669946 0.9699428 0.9692082
## [15] 0.9686232 0.9680810 0.9679888 0.9719076 0.9737659 0.9717287 0.9721527
## [22] 0.9739106 0.9850316 0.9754519 0.9773278 0.9803752 0.9790203 0.9781898
## [29] 0.9827476 0.9820912 0.9804850 0.9824460 0.9842029 0.9863901 0.9826753
## [36] 0.9698795 0.9763349 0.9732616 0.9732240 0.9773656 0.9757184 0.9720196
## [43] 0.9758237 0.9776264 0.9773559 0.9760954 0.9721164 0.9740579 0.9762195
## [50] 0.9756204 0.9754483 0.9737954 0.9753881 0.9739766 0.9779405 0.9716947
## [57] 0.9761848 0.9750634 0.9822835 0.9819393 0.9786272 0.9785142 0.9854238
## [64] 0.9828127 0.9806645 0.9754916 0.9813994 0.9819919 0.9803952 0.9834335
## [71] 0.9844148 0.9800646 0.9809812 0.9816172 0.9797660 0.9770588 0.9812999
## [78] 0.9822142 0.9766992 0.9773403 0.9766287 0.9813166 0.9777956 0.9777998
## [85] 0.9817983 0.9821079 0.9763866 0.9792454 0.9827015 0.9817944 0.9797096
## [92] 0.9809084 0.9808134 0.9843007 0.9806357 0.9837552 0.9829367 0.9834845
## [99] 0.9833852 0.9833107 0.9836878 0.9832438 0.9852257 0.9878405 0.9859661
## [106] 0.9893246 0.9911503 0.9873899 0.9867398 0.9875612 0.9884403 0.9943063
## [113] 0.9927550 0.9901959 0.9912703 0.9912583 0.9858689 0.9836241 0.9917215
## [120] 0.9888040 0.9887349 0.9853497 0.9855746 0.9851983 0.9844187 0.9884564
## [127] 0.9930808 0.9909677 0.9923110 0.9915750 0.9922662 0.9892059 0.9924656
## [134] 0.9913146 0.9924557 0.9906471 0.9921133 0.9920285 0.9896524 0.9928773
## [141] 0.9913481 0.9903453 0.9911896 0.9920928 0.9904491 0.9891625 0.9897678
## [148] 0.9905157 0.9891034 0.9899743 0.9891386 0.9920950 0.9906200 0.9908147
## [155] 0.9907784 0.9908225 0.9915463 0.9895416 0.9917841 0.9917279 0.9918921
## [162] 0.9921155 0.9917477 0.9914895 0.9916408 0.9920698 0.9926006 0.9951448
## [169] 0.9929108 0.9924770 0.9919439 0.9921658 0.9919918 0.9922745 0.9923626
## [176] 0.9923398 0.9924635 0.9918061 0.9919710 0.9918910 0.9924655 0.9926103
## [183] 0.9929377 0.9928635 0.9930645 0.9933544 0.9933080 0.9934548 0.9936806
## [190] 0.9937968 0.9938332 0.9949383 0.9955134 0.9952844 0.9952719 0.9955108
## [197] 0.9958916 0.9963991 0.9961893 0.9966793 0.9965589 0.9965200 0.9968591
## [204] 0.9971446 0.9969905 0.9969076 0.9968916 0.9974720 0.9973005 0.9971398
## [211] 0.9971816 0.9974619 0.9972727 0.9973622 0.9976526 0.9978557 0.9976591
## [218] 0.9977983 0.9981836 0.9981311 0.9980282 0.9983106 0.9982948 0.9982715
## [225] 0.9986057 0.9984973 0.9985954 0.9987211 0.9987352 0.9989175 0.9986715
## [232] 0.9987295 0.9985678 0.9989354 0.9987084 0.9989576 0.9989603 0.9990110
## [239] 0.9990041 0.9989316 0.9988641 0.9991205 0.9992412 0.9991843 0.9993130
## [246] 0.9992913 0.9994549 0.9994100 0.9995043 0.9994221 0.9993877 0.9994034
## [253] 0.9994913 0.9994190 0.9995926 0.9995088 0.9996031 0.9995064 0.9995966
## [260] 0.9995450 0.9996279 0.9995697 0.9995070 0.9996579 0.9995903 0.9995521Figure 1
fullanalysis = rbind(parts,whole) %>%
mutate(Method =
factor(Method,
levels=c('iTFR','iTFR+','xTFR','xTFR+','bTFR','rele'),
labels=c('iTFR','iTFR+','xTFR','xTFR+','bTFR','Rele'),
ordered=TRUE
)) %>%
filter(Method %in% c('iTFR','iTFR+','xTFR','xTFR+','bTFR'))
## arrange the vertical plotting order (20 is top, 1 is bottom)
ord = tribble(
~'i', ~'Data', ~'Method',
20, 'All Data', 'iTFR',
19, 'All Data', 'iTFR+',
18, 'All Data', 'xTFR',
17, 'All Data', 'xTFR+',
16, 'All Data', 'bTFR',
14, 'HMD/HFD', 'iTFR',
13, 'HMD/HFD', 'iTFR+',
12, 'HMD/HFD', 'xTFR',
11, 'HMD/HFD', 'xTFR+',
10, 'HMD/HFD', 'bTFR',
8, 'DHS', 'iTFR',
7, 'DHS', 'iTFR+',
6, 'DHS', 'xTFR',
5, 'DHS', 'xTFR+',
4, 'DHS', 'bTFR',
2, 'US counties','iTFR',
1, 'US counties','xTFR'
)
fullanalysis = fullanalysis %>%
left_join(ord, by=c('Data','Method'))
b<- ggplot(data = fullanalysis,
aes(x=A50,y=i,
color=Method,
group=Method,
label=paste0(Method,' (',n,')'))) +
geom_point( size=2) +
geom_text(x=fullanalysis$A90+0.05, y=fullanalysis$i,
size=3, hjust=0, color='black') +
geom_segment( x=fullanalysis$A10, xend=fullanalysis$A90,
y=fullanalysis$i, yend=fullanalysis$i,
lwd=1) +
geom_hline(yintercept=c(15,9,3)) +
geom_vline(xintercept=0) +
geom_vline(xintercept=-1) +
scale_color_discrete(guide=FALSE) +
theme(axis.line.y = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
panel.grid.major.x = element_line(color='darkgrey')) +
scale_x_continuous(breaks=seq(-0,1,0.25), limits=c(-0.2,1.1)) +
labs(x='Absolute Error (Births/Woman)',
y='') +
geom_text(x= -.25, y=18, label='ALL\nDATA\nCOMBINED',
color='black',hjust= 0, size=4) +
geom_text(x= -.25, y=12, label='HMD/HFD',
color='black',hjust= 0, size=4) +
geom_text(x= -.25, y=6, label='DHS',
color='black',hjust= 0, size=4) +
geom_text(x= -.25, y=1.5, label='US\nCOUNTIES',
color='black',hjust= 0, size=4)
b
Absolute Error (Births/Woman) in TFR over alternative methods and datasets. Solid dots are at median Error for each method and dataset. Horizontal bars extend from the 10th-90th percentile of Error. Numbers in parentheses indicate the count of schedules for which it is possible to use each method. Median errors are within 1/10th of a birth across all data sets.
Figure 2
wild50thabs <- quantile(abs(combined$iTFR / combined$TFR_table -1), 0.5)
wild90thabs <- quantile(abs(combined$iTFR / combined$TFR_table -1), 0.9)
# Making the Primate graphic
ggplot(combined, aes(x = TFR_table, y = iTFR)) +
geom_point(shape = 19, color = 'gray', size = 3) +
geom_line(aes(x = TFR_table, y = 0.9 * TFR_table), lty = 2, lwd = 1, col = 'black') +
geom_line(aes(x = TFR_table, y = 1.1 * TFR_table), lty = 2, lwd = 1, col = 'black') +
geom_text_repel(aes(label = Species), hjust = 0, vjust = 0) +
annotate("text", label = paste0("50th percentile APE: ", percent(round(wild50thabs, 4))), x = 4, y = 10) +
annotate("text", label = paste0("90th percentile APE: ", percent(round(wild90thabs, 4))), x = 4, y = 9.5) +
theme_bw() +
geom_abline(slope = 1) +
xlim(2.9, 11) +
ylim(2.9, 11) +
theme(text = element_text(face = 'bold')) +
labs(x = 'TFR(Data)',
y = 'iTFR')
Fertility estimates for animal populations. \(iTFR\) estimates from nonhuman age-sex distributions. Observed TFR versus \(iTFR\) estimates for the species listed in . Estimates match observations along the 45-degree line; dashed lines represent +/- 10% errors.
Figure 3
# Making the Figure 1 graphic
figure1_func = function(method, color){
a <- ggplot(data=big, aes(shape = source)) +
geom_text(x=2, y=5.5, label= paste0(method),
color='black', size =4) +
geom_point(alpha=.80, color='black',
shape='+', size=1,
aes_string(x = big$lagTFR,
y = big[[paste0(method)]])) +
geom_abline(intercept=0,slope=1, alpha=.25) +
geom_abline(slope = 0.9, lty=2, lwd=0.25, col='black', alpha=.50) +
geom_abline(slope = 1.1, lty=2, lwd=0.25, col='black', alpha=.50) +
theme_bw() +
theme(legend.position="none",
plot.background = element_rect(fill = paste0(color)))+
theme(text=element_text(face='bold', size=9)) +
xlim(0.9,8) + ylim(0.9,8) +
labs(x='TFR (Data)', y='TFR (Estimate)')
return(a)
}
figure2_func = function(method, color){
dif<- (big[[paste0(method)]] - big$lagTFR)/ big$lagTFR*100
a <- ggplot(data=big, aes(shape = source)) +
geom_point(alpha=.80, color='black',
shape='+', size=1,
aes_string(x = "C", y = dif)) +
geom_hline(yintercept = 0) +
geom_hline(yintercept = 10, lty=2, lwd=0.5)+
geom_hline(yintercept = -10, lty=2, lwd=0.5)+
theme_bw() +
theme(legend.position="none",
text=element_text(face='bold', size=9),
plot.background = element_rect(fill = paste0(color))) +
ylim(-30,30) +
scale_x_log10(breaks = trans_breaks("log10", function(x) 10^x),
labels = trans_format("log10", math_format(10^.x))) +
labs( x='Population', y='% Error')
return(a)
}
figure3_func = function(method, color){
dif<- (big[[paste0(method)]] - big$lagTFR)/ big$lagTFR*100
a <- ggplot(data=big, aes(shape = source)) +
geom_point(alpha=.80, color='black',
shape='+', size=1,
aes_string(x = "Year", y = dif)) +
geom_hline(yintercept = 0) +
geom_hline(yintercept = 10, lty=2, lwd=0.5)+
geom_hline(yintercept = -10, lty=2, lwd=0.5)+
theme_bw() +
theme(legend.position="none",
text=element_text(face='bold', size=9),
plot.background = element_rect(fill = paste0(color))) +
xlim(1891,2015) + ylim(-30,30) +
labs(x='Year', y='% Error')
return(a)
}
itfr_1 <- figure1_func("iTFR", "lightcoral")
xtfr_1 <- figure1_func("xTFR", "lightblue")
bayestfr_1 <- figure1_func("bTFR", "lightgreen")
itfr_2 <- figure2_func("iTFR", "lightcoral")
xtfr_2 <- figure2_func("xTFR", "lightblue")
bayestfr_2 <- figure2_func("bTFR", "lightgreen")
itfr_3 <- figure3_func("iTFR", "lightcoral")
xtfr_3 <- figure3_func("xTFR", "lightblue")
bayestfr_3 <- figure3_func("bTFR", "lightgreen")
f1j<- ggplot() +
stat_density(data=big, aes(x=iTFR-lagTFR), geom='line', adjust=1.5,col='lightcoral', lwd=1) +
stat_density(data=big,geom='line', aes(x=bTFR-lagTFR),adjust=1.5, col='green', lwd=1) +
stat_density(data=big, aes(x=xTFR-lagTFR),geom='line', adjust=1.5, col="lightblue", lwd=1)+
geom_vline(xintercept=0) +
theme_bw() +
xlim(-0.5,0.5) +
theme(text=element_text(face='bold', size=9)) +
labs(x='Algebraic Error',
y='Density')
f1k<- ggplot() +
stat_density(data=big, aes(x=abs((iTFR-lagTFR))), adjust=1.5,col='lightcoral', lwd=1, geom='line') +
stat_density(data=big, aes(x=abs((bTFR-lagTFR))),adjust=1.5, col='green', lwd=1, geom='line') +
stat_density(data=big, aes(x=abs((xTFR-lagTFR))), adjust=1.5, col="lightblue", lwd=1, geom='line')+
geom_vline(xintercept=0) +
theme_bw() +
xlim(0,+.50) +
theme(text=element_text(face='bold', size=9)) +
labs(x='Absolute Algebraic Error',
y='Density')
f1l<- ggplot() +
stat_density(data=big, aes(x=abs((iTFR-lagTFR)/lagTFR)*100), adjust=1.5,col='lightcoral', lwd=1, geom='line') +
stat_density(data=big, aes(x=abs((bTFR-lagTFR)/lagTFR)*100),adjust=1.5, col='green', lwd=1, geom='line') +
stat_density(data=big, aes(x=abs((xTFR-lagTFR)/lagTFR)*100), adjust=1.5, col="lightblue", lwd=1, geom='line')+
geom_vline(xintercept=0) +
theme_bw() +
xlim(0,25) +
theme(text=element_text(face='bold', size=9)) +
labs(x='Absolute Percent Error',
y='Density')
plot_grid(itfr_1, xtfr_1, bayestfr_1,
itfr_2, xtfr_2, bayestfr_2,
itfr_3, xtfr_3, bayestfr_3,
f1j, f1k, f1l,
labels = "auto", ncol=3, label_y=0.3, label_x=0)
Estimated TFR from Population Pyramids. Performance of three variants in HFD and DHS data. (a, d, g) use \(iTFR\); (b, e, h) use \(xTFR\); (c, f, i) use \(bTFR\); (a, b, c) plot estimated TFR against the observed 5-year average TFR. The solid line is \(Y=X\), and the dashed lines are \(\pm 10\%\). (d, e, f) illustrate percent error against population size. The dashed lines represent errors of \(\pm 10\%\). (g, h, i) plot percent errors against the year in which the population pyramid is observed. (j) plots the distribution of algebraic errors for each method (\(est-obs\)). (k) plots the distribution of absolute algebraic errors. (l) plots the distribution of absolute percent errors. For all variants, estimates are accurate over many scales and times.
Figure 4
err_q5 = function(df,err, color){
errs <- abs(df[[paste0(err)]] / df$lagTFR -1)
a<- ggplot(data=df) +
geom_point(alpha=.80, color='black',
shape='+', size=1,
aes(x = 1000*q5, y = abs(df[[err]] / df$lagTFR -1)*100)) +
geom_smooth(aes(x = 1000*q5, y = errs*100), color = 'black') +
theme_bw() +
geom_hline(yintercept=10,lty=2, lwd=0.5, col='black') +
geom_text(x=50, y=20, label= paste0(err), color='black', size =4) +
coord_cartesian(ylim = c(0, 25)) +
theme(text=element_text(face='bold', size=9),
plot.background = element_rect(fill = paste0("light", color))) +
labs(x = "q(5), per 1000",
y = "APE")
return(a)
}
a<- err_q5(big,"iTFR", "coral")
b<- err_q5(big,"iTFR+", "coral")
c<- err_q5(big,"xTFR", "blue")
d<- err_q5(big,"xTFR+", "blue")
e<- err_q5(big,"bTFR", "green")
plot_grid(a,b,c,d,e, labels = 'auto', ncol = 2)
Absolute Percent Errors against \(q_5\) values in the HMD and DHS. We compare the performance of the five variants against observed \(q_5\) mortality rates. As \(q_5\) values increase, APE also increases in the \(iTFR\) and \(xTFR\) variants. This is corrected in the \(iTFR^+\), \(xTFR^+\), and \(bTFR\) variants, which incorporate estimated child mortality.
Figure 5
Note: The African 1 sq. km raster data can be downloaded from WorldPop at: http://www.worldpop.org.uk/data/summary/?id=337
packages <- function(x){
x <- deparse(substitute(x))
installed_packages <- as.character(installed.packages()[,1])
if (length(intersect(x, installed_packages)) == 0){
install.packages(pkgs = x, dependencies = TRUE, repos = "http://cran.r-project.org")
}
library(x, character.only = TRUE)
rm(installed_packages) # Remove From Workspace
}
packages(tidyverse)
packages(ggrepel)
packages(grid)
packages(gridExtra)
packages(HMDHFDplus)
packages(scales)
packages(dplyr)
packages(openxlsx)
packages(tmap)
packages(tmaptools)
packages(tigris)
packages(censusapi)
packages(tidycensus)
packages(cowplot)
packages(magick)
packages(pdftools)
packages(readxl)
packages(ggpubr)
packages(wpp2017)
packages(raster)
packages(rgdal)
packages(sf)
# q5 data comes from the UN's World Population Prospects
countryq5 <- read.xlsx("../R/DATA-RAW/AFRICA/WPP2017_MORT_F01_2_Q5_BOTH_SEXES.xlsx", sheet=1) %>% dplyr::select(X3, X18) %>% na.omit %>%
rename(Country = X3, q5_2015 = X18) %>%
mutate(q5_2015 = as.numeric(q5_2015)/1000)
borders <- read_sf("../R/DATA-RAW/AFRICA/TM_WORLD_BORDERS-0.3/Africa.shp") %>%
mutate(NAME = case_when(
NAME == "Libyan Arab Jamahiriya" ~"Libya",
NAME == "Cape Verde" ~ "Cabo Verde",
NAME == "Cote d'Ivoire" ~ "Côte d'Ivoire",
TRUE ~ as.character(NAME))) %>%
append_data(., countryq5, key.shp = "NAME", key.data = "Country")
# The WorldPop data is too large to host on GitHub. To fully replicate, you'll need to download the files from WorldPop
# and populate the folder yourself.
# Note: The African 1 sq. km raster data can be downloaded from WorldPop at: http://www.worldpop.org.uk/data/summary/?id=337
# #----ITFR AFRICA----
# # Reading the gridded population data from WorldPop for the year 2015
# f0004_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A0004_F_2015_adj_v5.tif")
# m0004_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A0004_M_2015_adj_v5.tif")
# f1519_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A1519_F_2015_adj_v5.tif")
# f2024_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A2024_F_2015_adj_v5.tif")
# f2529_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A2529_F_2015_adj_v5.tif")
# f3034_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A3034_F_2015_adj_v5.tif")
# f3539_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A3539_F_2015_adj_v5.tif")
# f4044_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A4044_F_2015_adj_v5.tif")
# f4549_2015 <- raster("../R/DATA-RAW/Worldpop/AFR_PPP_A4549_F_2015_adj_v5.tif")
# q5 <- rasterize(borders, f0004_2015, 'q5_2015')
#
# # Calculating the xTFR based on the coefficients from above
# iTFR_worldpop <- overlay(f0004_2015,
# m0004_2015,
# f1519_2015,
# f2024_2015,
# f2529_2015,
# f3034_2015,
# f3539_2015,
# f4044_2015,
# f4549_2015,
# q5missing,
# fun=function(r1,r2,r3,r4,r5,r6,r7,r8,r9,r10){
# C = (r1+r2)
# W = (r3+r4+r5+r6+r7+r8+r9)
# return(7 * (C/(1-0.8*r10)/W))})
#
# writeRaster(iTFR_worldpop, filename="DATA-PROCESSED/AFRICA-iTFRplus_worldpop.tif", format="GTiff", overwrite=TRUE)
rasterDF <- raster("../R/DATA-PROCESSED/AFRICA-iTFRplus_worldpop.tif")
# Reading the boundary files for Africa
borders <- read_sf("../R/DATA-RAW/AFRICA/TM_WORLD_BORDERS-0.3/Africa.shp") %>%
mutate(NAME = case_when(
NAME == "Libyan Arab Jamahiriya" ~"Libya",
NAME == "United Republic of Tanzania" ~ "Tanzania",
NAME == "Democratic Republic of the Congo" ~ "DR Congo",
TRUE ~ as.character(NAME)))
# Setting the color ramps
rampcols <- c("#2b8cbe", brewer.pal(8, "YlOrRd"))
# Setting the bounding box of the map to just the outline of Africa
africa_bb <- bb(rasterDF, xlim=c(.14, .82), ylim=c(0.15, .96), relative = TRUE)
# Mapping the gridded TFRS
a <- tm_shape(rasterDF, bbox = africa_bb) +
tm_raster("AFRICA.iTFRplus_worldpop",
palette = rampcols,
breaks = c(0, 2.1, 3, 4, 5, 6, 7, 8, 9, Inf),
title = "TFR") +
tm_shape(borders) +
tm_borders(lwd=2, col="black", alpha = 0.5) +
tm_text("NAME" , size="AREA", root=5, legend.size.show = FALSE) +
tm_layout(legend.position = c("left","bottom"),
legend.bg.color = "white",
legend.text.size = 0.9,
legend.format = list(digits=1))
a
Estimating subnational fertility rates. We use the \(iTFR^+\) method to estimate subnational total fertility rates for the African continent for 2010-2015 using data from WorldPop and the United Nations WPP 2017.
# save_tmap(a, filename="./MANUSCRIPT/FIGURES/top_africa4.pdf")Figure 6
# Data are produced from
results <- read_csv('../R/DATA-PROCESSED/HMDHFD-allbTFR_06172017.csv') %>%
filter(Code %in% c("NLD", "SWE", "FRATNP", "ITA")) %>%
dplyr::select(-lagTFR)
historical <- read_csv("../R/DATA-PROCESSED/001-LoadCleanHFDHMDData.csv") %>%
dplyr::select(Code, Year, TFR, lagTFR)
# Getting data from the HFC
z <- rbind(read_csv("https://www.fertilitydata.org/data/SWE/SWE_TFRMAB_TOT.txt"),
read_csv("https://www.fertilitydata.org/data/FRA/FRA_TFRMAB_TOT.txt"),
read_csv("https://www.fertilitydata.org/data/ITA/ITA_TFRMAB_TOT.txt"),
read_csv("https://www.fertilitydata.org/data/NLD/NLD_TFRMAB_TOT.txt")) %>%
filter(RefCode %in% c("SWE_02", "FRA_03", "ITA_13", "NLD_02")) %>%
mutate(Country = if_else(Country == "FRA", "FRATNP", Country)) %>%
group_by(Country, AgeDef) %>%
mutate(length = Year2 - Year1 +1,
lagTFR = if_else(length == 1, mean_lag5(TFR), TFR )) %>%
dplyr::select(Code = Country, Year = Year2, HFC = lagTFR)
results2 <- results %>%
left_join(., historical) %>%
mutate(country = case_when(
Code == "SWE" ~ "Sweden",
Code == "NLD" ~ "Netherlands",
Code == "FRATNP" ~ "France",
Code == "ITA" ~ "Italy"
)) %>%
left_join(., z)
ggplot(data = results2) +
geom_ribbon(aes(x=Year, ymin=Q10, ymax=Q90), fill = "gray", alpha=0.6) +
geom_line(aes(x=Year, y = post_mean, linetype = "bTFR")) +
geom_point(aes(x=Year, y = lagTFR, shape = "Observed", color = "Observed"), alpha= 0.3, size =2) +
geom_point(aes(x=Year, y = HFC, shape = "HFC", color = "HFC"), alpha= 0.5, size =2) +
scale_y_continuous(limits = c(1,7), expand = c(0, 0)) +
theme(text=element_text(face='bold', size = 8),
legend.text=element_text(size=5))+
theme(legend.position=c(0.22,0.17),
legend.key.size = unit(0.25, "cm")) +
scale_shape_manual("",
values = c(42,1)) +
scale_color_manual("",
values = c("red", "black")) +
scale_linetype_manual("", values = "solid") +
theme_bw() +
theme(legend.position="bottom") +
labs(x='Year', y='TFR') +
scale_x_continuous(breaks = c(1750,1800,1850,1900,1950,2000)) +
facet_wrap(~country) 
Estimating historical fertility. \(bTFR\) estimates of period fertility rates in four European countries using HMD historical age-sex and child mortality data. Shaded regions represent 90 percent posterior probability intervals; open circles are observed TFRs from the HFD. Red stars are average TFRs over the preceding five-year period for the earliest series with a vital records source from the Human Fertility Collection .
Figure 7
# NOTE: To load data, you must download both the extract's data and the DDI
# and also set the working directory to the folder with these files (or change the path below).
library(tidyverse)
# graphics.off()
# windows(record=TRUE)
data.already.processed = TRUE
inc_cutoffs = c(-Inf, 25, 50, 75, 100, 150, 200, 250, 300, Inf)
inc_labels = c('<25','25-50','50-75','75-100',
'100-150','150-200',
'200-250','250-300','>300')
# if (!data.already.processed) {
#
# if (!require("ipumsr")) stop("Reading IPUMS data into R requires the ipumsr package. It can be installed using the following command: install.packages('ipumsr')")
#
# ddi <- read_ipums_ddi("../DATA-RAW/CPS/cps_00003.xml")
#
# # select March supplement data only
#
# data <- read_ipums_micro(ddi) %>%
# filter( ASECFLAG==1 )
#
#
#
#
# case = expand.grid(this_race = c('White','Non-White'),
# this_income = inc_labels)
#
#
# case$xTFR = NA
# case$Q05 = NA
# case$Q95 = NA
#
#
# xTFR_star = function(ix,mydata) {
# C = sum(mydata$C[ix])
# W15 = sum(mydata$W15[ix])
# W20 = sum(mydata$W20[ix])
# W25 = sum(mydata$W25[ix])
# W30 = sum(mydata$W30[ix])
# W35 = sum(mydata$W35[ix])
# W40 = sum(mydata$W40[ix])
# W45 = sum(mydata$W45[ix])
#
# W = (W15+W20+W25+W30+W35+W40+W45)
# pi2534 = (W25 + W30) / W
#
# xTFR = (10.65 - 12.55 * pi2534) * C/W
#
# return(xTFR)
# }
#
#
#
# for (icase in 1:nrow(case)) {
#
# this_race = case$this_race[icase]
# this_income = case$this_income[icase]
#
# print(this_race)
# print(this_income)
#
# mydata = data %>%
# mutate(income_cat = cut(HHINCOME/1000,
# breaks=inc_cutoffs,
# labels=inc_labels),
# age = 5*floor(AGE/5),
# sex = SEX,
# race_eth = case_when(
# RACE == 100 ~ "White",
# TRUE ~ "Non-White"
# )) %>%
# filter(race_eth == this_race,
# income_cat == this_income) %>%
# group_by(YEAR,SERIAL) %>%
# summarize( income = income_cat[1],
# race = race_eth[1],
# C = sum(ASECWT[ age== 0 ]),
# W15 = sum(ASECWT[(age==15) & sex==2]),
# W20 = sum(ASECWT[(age==20) & sex==2]),
# W25 = sum(ASECWT[(age==25) & sex==2]),
# W30 = sum(ASECWT[(age==30) & sex==2]),
# W35 = sum(ASECWT[(age==35) & sex==2]),
# W40 = sum(ASECWT[(age==40) & sex==2]),
# W45 = sum(ASECWT[(age==45) & sex==2])
# )
#
# HH = nrow(mydata)
# print(paste(HH,'households'))
#
# imat = matrix(NA, nrow(mydata), 1000)
#
# for (j in 1:ncol(imat)) { imat[,j] = sample(nrow(mydata), replace=TRUE) }
#
# # calculate xTFR from a vector of indices
# est = xTFR_star(1:nrow(mydata), mydata)
#
# case$xTFR[icase] = est
#
# z = sapply(1:ncol(imat), function(j) { xTFR_star(imat[,j], mydata)})
#
# Q = quantile(z, probs=c(.05,.95))
#
# case$Q05[icase] = Q[1]
# case$Q95[icase] = Q[2]
#
# print(case[icase,])
#
# plot( density(z, adj=1.5), xlim=c(1,3),
# main=paste(case$this_race[icase], case$this_income[icase]))
# abline(v=c(Q,est), lty=2, col='red')
#
# } # for icase
#
#
# write.csv(case, file='../DATA-PROCESSED/CPS-income-race.csv')
#
# } else {
# case = read.csv(file='../DATA-PROCESSED/CPS-income-race.csv') %>%
# mutate( this_income = factor(this_income, levels=inc_labels),
# this_race = factor(this_race,levels=c('White','Non-White')))
# }
case = read_csv(file='../R/DATA-PROCESSED/CPS-income-race.csv') %>%
mutate( this_income = factor(this_income, levels=inc_labels),
this_race = factor(this_race,levels=c('White','Non-White')))
ggplot(data=case,
aes(x=this_income,y=xTFR,
shape=this_race, group=this_race, color=this_race)) +
geom_ribbon(aes(ymin = Q05, ymax = Q95, fill = this_race), color = NA, alpha = 0.3) +
geom_line(linetype=2) +
geom_point(size=3.5) +
scale_shape_manual(values=c('W','N'), guide=FALSE) +
scale_y_continuous(breaks=seq(1.6,2.6,0.2)) +
geom_hline(yintercept = 2) +
theme_bw() +
theme(axis.title=element_text(size=14,face="bold")) +
labs(x='Household Income in Thousands',
y='TFR') +
scale_color_manual(values=c('red','blue'), guide=FALSE) +
geom_text(x=7.5,y=2.7,size=7,label='Non-White', color='black') +
geom_text(x=8.5,y=1.7,size=7,label='White', color='black') +
guides(fill=FALSE)
Total Fertility (\(xTFR\)) by race and household income level. We estimate TFR from age-sex distributions within race-income categories using the U.S. Current Population Survey (CPS) March Social and Economic Supplements, combined over 2010-2018. White corresponds to those reporting their race as White only; Non-White corresponds to all other survey respondents. Shaded regions represent confidence intervals (5%-95%) estimated from 1000 bootstrap samples in which households in each rae-income category are drawn randomly with replacement from the set of all CPS households.